The Effect of Automatic Speech Recognition Eyespeak Software on Iraqi Students' English Pronunciation: A Pilot Study

ERIC Educational Resources Information Center

Sidgi, Lina Fathi Sidig; Shaari, Ahmad Jelani

2017-01-01

The use of technology, such as computer-assisted language learning (CALL), is used in teaching and learning in the foreign language classrooms where it is most needed. One promising emerging technology that supports language learning is automatic speech recognition (ASR). Integrating such technology, especially in the instruction of pronunciation…

Using Automatic Speech Recognition Technology with Elicited Oral Response Testing

ERIC Educational Resources Information Center

Cox, Troy L.; Davies, Randall S.

2012-01-01

This study examined the use of automatic speech recognition (ASR) scored elicited oral response (EOR) tests to assess the speaking ability of English language learners. It also examined the relationship between ASR-scored EOR and other language proficiency measures and the ability of the ASR to rate speakers without bias to gender or native…

Female voice communications in high level aircraft cockpit noises--part II: vocoder and automatic speech recognition systems.

PubMed

Nixon, C; Anderson, T; Morris, L; McCavitt, A; McKinley, R; Yeager, D; McDaniel, M

1998-11-01

The intelligibility of female and male speech is equivalent under most ordinary living conditions. However, due to small differences between their acoustic speech signals, called speech spectra, one can be more or less intelligible than the other in certain situations such as high levels of noise. Anecdotal information, supported by some empirical observations, suggests that some of the high intensity noise spectra of military aircraft cockpits may degrade the intelligibility of female speech more than that of male speech. In an applied research study, the intelligibility of female and male speech was measured in several high level aircraft cockpit noise conditions experienced in military aviation. In Part I, (Nixon CW, et al. Aviat Space Environ Med 1998; 69:675-83) female speech intelligibility measured in the spectra and levels of aircraft cockpit noises and with noise-canceling microphones was lower than that of the male speech in all conditions. However, the differences were small and only those at some of the highest noise levels were significant. Although speech intelligibility of both genders was acceptable during normal cruise noises, improvements are required in most of the highest levels of noise created during maximum aircraft operating conditions. These results are discussed in a Part I technical report. This Part II report examines the intelligibility in the same aircraft cockpit noises of vocoded female and male speech and the accuracy with which female and male speech in some of the cockpit noises were understood by automatic speech recognition systems. The intelligibility of vocoded female speech was generally the same as that of vocoded male speech. No significant differences were measured between the recognition accuracy of male and female speech by the automatic speech recognition systems. The intelligibility of female and male speech was equivalent for these conditions.

Assessment of Severe Apnoea through Voice Analysis, Automatic Speech, and Speaker Recognition Techniques

NASA Astrophysics Data System (ADS)

Fernández Pozo, Rubén; Blanco Murillo, Jose Luis; Hernández Gómez, Luis; López Gonzalo, Eduardo; Alcázar Ramírez, José; Toledano, Doroteo T.

2009-12-01

This study is part of an ongoing collaborative effort between the medical and the signal processing communities to promote research on applying standard Automatic Speech Recognition (ASR) techniques for the automatic diagnosis of patients with severe obstructive sleep apnoea (OSA). Early detection of severe apnoea cases is important so that patients can receive early treatment. Effective ASR-based detection could dramatically cut medical testing time. Working with a carefully designed speech database of healthy and apnoea subjects, we describe an acoustic search for distinctive apnoea voice characteristics. We also study abnormal nasalization in OSA patients by modelling vowels in nasal and nonnasal phonetic contexts using Gaussian Mixture Model (GMM) pattern recognition on speech spectra. Finally, we present experimental findings regarding the discriminative power of GMMs applied to severe apnoea detection. We have achieved an 81% correct classification rate, which is very promising and underpins the interest in this line of inquiry.

Speech Recognition as a Support Service for Deaf and Hard of Hearing Students: Adaptation and Evaluation. Final Report to Spencer Foundation.

ERIC Educational Resources Information Center

Stinson, Michael; Elliot, Lisa; McKee, Barbara; Coyne, Gina

This report discusses a project that adapted new automatic speech recognition (ASR) technology to provide real-time speech-to-text transcription as a support service for students who are deaf and hard of hearing (D/HH). In this system, as the teacher speaks, a hearing intermediary, or captionist, dictates into the speech recognition system in a…

The Use of an Autonomous Pedagogical Agent and Automatic Speech Recognition for Teaching Sight Words to Students with Autism Spectrum Disorder

ERIC Educational Resources Information Center

Saadatzi, Mohammad Nasser; Pennington, Robert C.; Welch, Karla C.; Graham, James H.; Scott, Renee E.

2017-01-01

In the current study, we examined the effects of an instructional package comprised of an autonomous pedagogical agent, automatic speech recognition, and constant time delay during the instruction of reading sight words aloud to young adults with autism spectrum disorder. We used a concurrent multiple baseline across participants design to…

Modelling Errors in Automatic Speech Recognition for Dysarthric Speakers

NASA Astrophysics Data System (ADS)

Caballero Morales, Santiago Omar; Cox, Stephen J.

2009-12-01

Dysarthria is a motor speech disorder characterized by weakness, paralysis, or poor coordination of the muscles responsible for speech. Although automatic speech recognition (ASR) systems have been developed for disordered speech, factors such as low intelligibility and limited phonemic repertoire decrease speech recognition accuracy, making conventional speaker adaptation algorithms perform poorly on dysarthric speakers. In this work, rather than adapting the acoustic models, we model the errors made by the speaker and attempt to correct them. For this task, two techniques have been developed: (1) a set of "metamodels" that incorporate a model of the speaker's phonetic confusion matrix into the ASR process; (2) a cascade of weighted finite-state transducers at the confusion matrix, word, and language levels. Both techniques attempt to correct the errors made at the phonetic level and make use of a language model to find the best estimate of the correct word sequence. Our experiments show that both techniques outperform standard adaptation techniques.

Speech recognition for embedded automatic positioner for laparoscope

NASA Astrophysics Data System (ADS)

Chen, Xiaodong; Yin, Qingyun; Wang, Yi; Yu, Daoyin

2014-07-01

In this paper a novel speech recognition methodology based on Hidden Markov Model (HMM) is proposed for embedded Automatic Positioner for Laparoscope (APL), which includes a fixed point ARM processor as the core. The APL system is designed to assist the doctor in laparoscopic surgery, by implementing the specific doctor's vocal control to the laparoscope. Real-time respond to the voice commands asks for more efficient speech recognition algorithm for the APL. In order to reduce computation cost without significant loss in recognition accuracy, both arithmetic and algorithmic optimizations are applied in the method presented. First, depending on arithmetic optimizations most, a fixed point frontend for speech feature analysis is built according to the ARM processor's character. Then the fast likelihood computation algorithm is used to reduce computational complexity of the HMM-based recognition algorithm. The experimental results show that, the method shortens the recognition time within 0.5s, while the accuracy higher than 99%, demonstrating its ability to achieve real-time vocal control to the APL.

Effect of speech-intrinsic variations on human and automatic recognition of spoken phonemes.

PubMed

Meyer, Bernd T; Brand, Thomas; Kollmeier, Birger

2011-01-01

The aim of this study is to quantify the gap between the recognition performance of human listeners and an automatic speech recognition (ASR) system with special focus on intrinsic variations of speech, such as speaking rate and effort, altered pitch, and the presence of dialect and accent. Second, it is investigated if the most common ASR features contain all information required to recognize speech in noisy environments by using resynthesized ASR features in listening experiments. For the phoneme recognition task, the ASR system achieved the human performance level only when the signal-to-noise ratio (SNR) was increased by 15 dB, which is an estimate for the human-machine gap in terms of the SNR. The major part of this gap is attributed to the feature extraction stage, since human listeners achieve comparable recognition scores when the SNR difference between unaltered and resynthesized utterances is 10 dB. Intrinsic variabilities result in strong increases of error rates, both in human speech recognition (HSR) and ASR (with a relative increase of up to 120%). An analysis of phoneme duration and recognition rates indicates that human listeners are better able to identify temporal cues than the machine at low SNRs, which suggests incorporating information about the temporal dynamics of speech into ASR systems.

Automatic speech recognition (ASR) based approach for speech therapy of aphasic patients: A review

NASA Astrophysics Data System (ADS)

Jamal, Norezmi; Shanta, Shahnoor; Mahmud, Farhanahani; Sha'abani, MNAH

2017-09-01

This paper reviews the state-of-the-art an automatic speech recognition (ASR) based approach for speech therapy of aphasic patients. Aphasia is a condition in which the affected person suffers from speech and language disorder resulting from a stroke or brain injury. Since there is a growing body of evidence indicating the possibility of improving the symptoms at an early stage, ASR based solutions are increasingly being researched for speech and language therapy. ASR is a technology that transfers human speech into transcript text by matching with the system's library. This is particularly useful in speech rehabilitation therapies as they provide accurate, real-time evaluation for speech input from an individual with speech disorder. ASR based approaches for speech therapy recognize the speech input from the aphasic patient and provide real-time feedback response to their mistakes. However, the accuracy of ASR is dependent on many factors such as, phoneme recognition, speech continuity, speaker and environmental differences as well as our depth of knowledge on human language understanding. Hence, the review examines recent development of ASR technologies and its performance for individuals with speech and language disorders.

Automatic speech recognition using a predictive echo state network classifier.

PubMed

Skowronski, Mark D; Harris, John G

2007-04-01

We have combined an echo state network (ESN) with a competitive state machine framework to create a classification engine called the predictive ESN classifier. We derive the expressions for training the predictive ESN classifier and show that the model was significantly more noise robust compared to a hidden Markov model in noisy speech classification experiments by 8+/-1 dB signal-to-noise ratio. The simple training algorithm and noise robustness of the predictive ESN classifier make it an attractive classification engine for automatic speech recognition.

Multilevel Analysis in Analyzing Speech Data

ERIC Educational Resources Information Center

Guddattu, Vasudeva; Krishna, Y.

2011-01-01

The speech produced by human vocal tract is a complex acoustic signal, with diverse applications in phonetics, speech synthesis, automatic speech recognition, speaker identification, communication aids, speech pathology, speech perception, machine translation, hearing research, rehabilitation and assessment of communication disorders and many…

Speech Recognition Software for Language Learning: Toward an Evaluation of Validity and Student Perceptions

ERIC Educational Resources Information Center

Cordier, Deborah

2009-01-01

A renewed focus on foreign language (FL) learning and speech for communication has resulted in computer-assisted language learning (CALL) software developed with Automatic Speech Recognition (ASR). ASR features for FL pronunciation (Lafford, 2004) are functional components of CALL designs used for FL teaching and learning. The ASR features…

Voice technology and BBN

NASA Technical Reports Server (NTRS)

Wolf, Jared J.

1977-01-01

The following research was discussed: (1) speech signal processing; (2) automatic speech recognition; (3) continuous speech understanding; (4) speaker recognition; (5) speech compression; (6) subjective and objective evaluation of speech communication system; (7) measurement of the intelligibility and quality of speech when degraded by noise or other masking stimuli; (8) speech synthesis; (9) instructional aids for second-language learning and for training of the deaf; and (10) investigation of speech correlates of psychological stress. Experimental psychology, control systems, and human factors engineering, which are often relevant to the proper design and operation of speech systems are described.

I Hear You Eat and Speak: Automatic Recognition of Eating Condition and Food Type, Use-Cases, and Impact on ASR Performance

PubMed Central

Hantke, Simone; Weninger, Felix; Kurle, Richard; Ringeval, Fabien; Batliner, Anton; Mousa, Amr El-Desoky; Schuller, Björn

2016-01-01

We propose a new recognition task in the area of computational paralinguistics: automatic recognition of eating conditions in speech, i. e., whether people are eating while speaking, and what they are eating. To this end, we introduce the audio-visual iHEARu-EAT database featuring 1.6 k utterances of 30 subjects (mean age: 26.1 years, standard deviation: 2.66 years, gender balanced, German speakers), six types of food (Apple, Nectarine, Banana, Haribo Smurfs, Biscuit, and Crisps), and read as well as spontaneous speech, which is made publicly available for research purposes. We start with demonstrating that for automatic speech recognition (ASR), it pays off to know whether speakers are eating or not. We also propose automatic classification both by brute-forcing of low-level acoustic features as well as higher-level features related to intelligibility, obtained from an Automatic Speech Recogniser. Prediction of the eating condition was performed with a Support Vector Machine (SVM) classifier employed in a leave-one-speaker-out evaluation framework. Results show that the binary prediction of eating condition (i. e., eating or not eating) can be easily solved independently of the speaking condition; the obtained average recalls are all above 90%. Low-level acoustic features provide the best performance on spontaneous speech, which reaches up to 62.3% average recall for multi-way classification of the eating condition, i. e., discriminating the six types of food, as well as not eating. The early fusion of features related to intelligibility with the brute-forced acoustic feature set improves the performance on read speech, reaching a 66.4% average recall for the multi-way classification task. Analysing features and classifier errors leads to a suitable ordinal scale for eating conditions, on which automatic regression can be performed with up to 56.2% determination coefficient. PMID:27176486

Assessing Children's Home Language Environments Using Automatic Speech Recognition Technology

ERIC Educational Resources Information Center

Greenwood, Charles R.; Thiemann-Bourque, Kathy; Walker, Dale; Buzhardt, Jay; Gilkerson, Jill

2011-01-01

The purpose of this research was to replicate and extend some of the findings of Hart and Risley using automatic speech processing instead of human transcription of language samples. The long-term goal of this work is to make the current approach to speech processing possible by researchers and clinicians working on a daily basis with families and…

[Creating language model of the forensic medicine domain for developing a autopsy recording system by automatic speech recognition].

PubMed

Niijima, H; Ito, N; Ogino, S; Takatori, T; Iwase, H; Kobayashi, M

2000-11-01

For the purpose of practical use of speech recognition technology for recording of forensic autopsy, a language model of the speech recording system, specialized for the forensic autopsy, was developed. The language model for the forensic autopsy by applying 3-gram model was created, and an acoustic model for Japanese speech recognition by Hidden Markov Model in addition to the above were utilized to customize the speech recognition engine for forensic autopsy. A forensic vocabulary set of over 10,000 words was compiled and some 300,000 sentence patterns were made to create the forensic language model, then properly mixing with a general language model to attain high exactitude. When tried by dictating autopsy findings, this speech recognition system was proved to be about 95% of recognition rate that seems to have reached to the practical usability in view of speech recognition software, though there remains rooms for improving its hardware and application-layer software.

Development of A Two-Stage Procedure for the Automatic Recognition of Dysfluencies in the Speech of Children Who Stutter: I. Psychometric Procedures Appropriate for Selection of Training Material for Lexical Dysfluency Classifiers

PubMed Central

Howell, Peter; Sackin, Stevie; Glenn, Kazan

2007-01-01

This program of work is intended to develop automatic recognition procedures to locate and assess stuttered dysfluencies. This and the following article together, develop and test recognizers for repetitions and prolongations. The automatic recognizers classify the speech in two stages: In the first, the speech is segmented and in the second the segments are categorized. The units that are segmented are words. Here assessments by human judges on the speech of 12 children who stutter are described using a corresponding procedure. The accuracy of word boundary placement across judges, categorization of the words as fluent, repetition or prolongation, and duration of the different fluency categories are reported. These measures allow reliable instances of repetitions and prolongations to be selected for training and assessing the recognizers in the subsequent paper. PMID:9328878

Speech Clarity Index (Ψ): A Distance-Based Speech Quality Indicator and Recognition Rate Prediction for Dysarthric Speakers with Cerebral Palsy

NASA Astrophysics Data System (ADS)

Kayasith, Prakasith; Theeramunkong, Thanaruk

It is a tedious and subjective task to measure severity of a dysarthria by manually evaluating his/her speech using available standard assessment methods based on human perception. This paper presents an automated approach to assess speech quality of a dysarthric speaker with cerebral palsy. With the consideration of two complementary factors, speech consistency and speech distinction, a speech quality indicator called speech clarity index (Ψ) is proposed as a measure of the speaker's ability to produce consistent speech signal for a certain word and distinguished speech signal for different words. As an application, it can be used to assess speech quality and forecast speech recognition rate of speech made by an individual dysarthric speaker before actual exhaustive implementation of an automatic speech recognition system for the speaker. The effectiveness of Ψ as a speech recognition rate predictor is evaluated by rank-order inconsistency, correlation coefficient, and root-mean-square of difference. The evaluations had been done by comparing its predicted recognition rates with ones predicted by the standard methods called the articulatory and intelligibility tests based on the two recognition systems (HMM and ANN). The results show that Ψ is a promising indicator for predicting recognition rate of dysarthric speech. All experiments had been done on speech corpus composed of speech data from eight normal speakers and eight dysarthric speakers.

Effects and modeling of phonetic and acoustic confusions in accented speech.

PubMed

Fung, Pascale; Liu, Yi

2005-11-01

Accented speech recognition is more challenging than standard speech recognition due to the effects of phonetic and acoustic confusions. Phonetic confusion in accented speech occurs when an expected phone is pronounced as a different one, which leads to erroneous recognition. Acoustic confusion occurs when the pronounced phone is found to lie acoustically between two baseform models and can be equally recognized as either one. We propose that it is necessary to analyze and model these confusions separately in order to improve accented speech recognition without degrading standard speech recognition. Since low phonetic confusion units in accented speech do not give rise to automatic speech recognition errors, we focus on analyzing and reducing phonetic and acoustic confusability under high phonetic confusion conditions. We propose using likelihood ratio test to measure phonetic confusion, and asymmetric acoustic distance to measure acoustic confusion. Only accent-specific phonetic units with low acoustic confusion are used in an augmented pronunciation dictionary, while phonetic units with high acoustic confusion are reconstructed using decision tree merging. Experimental results show that our approach is effective and superior to methods modeling phonetic confusion or acoustic confusion alone in accented speech, with a significant 5.7% absolute WER reduction, without degrading standard speech recognition.

A Speech Recognition-based Solution for the Automatic Detection of Mild Cognitive Impairment from Spontaneous Speech

PubMed Central

Tóth, László; Hoffmann, Ildikó; Gosztolya, Gábor; Vincze, Veronika; Szatlóczki, Gréta; Bánréti, Zoltán; Pákáski, Magdolna; Kálmán, János

2018-01-01

Background: Even today the reliable diagnosis of the prodromal stages of Alzheimer’s disease (AD) remains a great challenge. Our research focuses on the earliest detectable indicators of cognitive de-cline in mild cognitive impairment (MCI). Since the presence of language impairment has been reported even in the mild stage of AD, the aim of this study is to develop a sensitive neuropsychological screening method which is based on the analysis of spontaneous speech production during performing a memory task. In the future, this can form the basis of an Internet-based interactive screening software for the recognition of MCI. Methods: Participants were 38 healthy controls and 48 clinically diagnosed MCI patients. The provoked spontaneous speech by asking the patients to recall the content of 2 short black and white films (one direct, one delayed), and by answering one question. Acoustic parameters (hesitation ratio, speech tempo, length and number of silent and filled pauses, length of utterance) were extracted from the recorded speech sig-nals, first manually (using the Praat software), and then automatically, with an automatic speech recogni-tion (ASR) based tool. First, the extracted parameters were statistically analyzed. Then we applied machine learning algorithms to see whether the MCI and the control group can be discriminated automatically based on the acoustic features. Results: The statistical analysis showed significant differences for most of the acoustic parameters (speech tempo, articulation rate, silent pause, hesitation ratio, length of utterance, pause-per-utterance ratio). The most significant differences between the two groups were found in the speech tempo in the delayed recall task, and in the number of pauses for the question-answering task. The fully automated version of the analysis process – that is, using the ASR-based features in combination with machine learning - was able to separate the two classes with an F1-score of 78.8%. Conclusion: The temporal analysis of spontaneous speech can be exploited in implementing a new, auto-matic detection-based tool for screening MCI for the community. PMID:29165085

A Speech Recognition-based Solution for the Automatic Detection of Mild Cognitive Impairment from Spontaneous Speech.

PubMed

Toth, Laszlo; Hoffmann, Ildiko; Gosztolya, Gabor; Vincze, Veronika; Szatloczki, Greta; Banreti, Zoltan; Pakaski, Magdolna; Kalman, Janos

2018-01-01

Even today the reliable diagnosis of the prodromal stages of Alzheimer's disease (AD) remains a great challenge. Our research focuses on the earliest detectable indicators of cognitive decline in mild cognitive impairment (MCI). Since the presence of language impairment has been reported even in the mild stage of AD, the aim of this study is to develop a sensitive neuropsychological screening method which is based on the analysis of spontaneous speech production during performing a memory task. In the future, this can form the basis of an Internet-based interactive screening software for the recognition of MCI. Participants were 38 healthy controls and 48 clinically diagnosed MCI patients. The provoked spontaneous speech by asking the patients to recall the content of 2 short black and white films (one direct, one delayed), and by answering one question. Acoustic parameters (hesitation ratio, speech tempo, length and number of silent and filled pauses, length of utterance) were extracted from the recorded speech signals, first manually (using the Praat software), and then automatically, with an automatic speech recognition (ASR) based tool. First, the extracted parameters were statistically analyzed. Then we applied machine learning algorithms to see whether the MCI and the control group can be discriminated automatically based on the acoustic features. The statistical analysis showed significant differences for most of the acoustic parameters (speech tempo, articulation rate, silent pause, hesitation ratio, length of utterance, pause-per-utterance ratio). The most significant differences between the two groups were found in the speech tempo in the delayed recall task, and in the number of pauses for the question-answering task. The fully automated version of the analysis process - that is, using the ASR-based features in combination with machine learning - was able to separate the two classes with an F1-score of 78.8%. The temporal analysis of spontaneous speech can be exploited in implementing a new, automatic detection-based tool for screening MCI for the community. Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.org.

Investigating Prompt Difficulty in an Automatically Scored Speaking Performance Assessment

ERIC Educational Resources Information Center

Cox, Troy L.

2013-01-01

Speaking assessments for second language learners have traditionally been expensive to administer because of the cost of rating the speech samples. To reduce the cost, many researchers are investigating the potential of using automatic speech recognition (ASR) as a means to score examinee responses to open-ended prompts. This study examined the…

Robot Command Interface Using an Audio-Visual Speech Recognition System

NASA Astrophysics Data System (ADS)

Ceballos, Alexánder; Gómez, Juan; Prieto, Flavio; Redarce, Tanneguy

In recent years audio-visual speech recognition has emerged as an active field of research thanks to advances in pattern recognition, signal processing and machine vision. Its ultimate goal is to allow human-computer communication using voice, taking into account the visual information contained in the audio-visual speech signal. This document presents a command's automatic recognition system using audio-visual information. The system is expected to control the laparoscopic robot da Vinci. The audio signal is treated using the Mel Frequency Cepstral Coefficients parametrization method. Besides, features based on the points that define the mouth's outer contour according to the MPEG-4 standard are used in order to extract the visual speech information.

Optimal pattern synthesis for speech recognition based on principal component analysis

NASA Astrophysics Data System (ADS)

Korsun, O. N.; Poliyev, A. V.

2018-02-01

The algorithm for building an optimal pattern for the purpose of automatic speech recognition, which increases the probability of correct recognition, is developed and presented in this work. The optimal pattern forming is based on the decomposition of an initial pattern to principal components, which enables to reduce the dimension of multi-parameter optimization problem. At the next step the training samples are introduced and the optimal estimates for principal components decomposition coefficients are obtained by a numeric parameter optimization algorithm. Finally, we consider the experiment results that show the improvement in speech recognition introduced by the proposed optimization algorithm.

Transcribe Your Class: Using Speech Recognition to Improve Access for At-Risk Students

ERIC Educational Resources Information Center

Bain, Keith; Lund-Lucas, Eunice; Stevens, Janice

2012-01-01

Through a project supported by Canada's Social Development Partnerships Program, a team of leading National Disability Organizations, universities, and industry partners are piloting a prototype Hosted Transcription Service that uses speech recognition to automatically create multimedia transcripts that can be used by students for study purposes.…

Use of Computer Speech Technologies To Enhance Learning.

ERIC Educational Resources Information Center

Ferrell, Joe

1999-01-01

Discusses the design of an innovative learning system that uses new technologies for the man-machine interface, incorporating a combination of Automatic Speech Recognition (ASR) and Text To Speech (TTS) synthesis. Highlights include using speech technologies to mimic the attributes of the ideal tutor and design features. (AEF)

Objective voice and speech analysis of persons with chronic hoarseness by prosodic analysis of speech samples.

PubMed

Haderlein, Tino; Döllinger, Michael; Matoušek, Václav; Nöth, Elmar

2016-10-01

Automatic voice assessment is often performed using sustained vowels. In contrast, speech analysis of read-out texts can be applied to voice and speech assessment. Automatic speech recognition and prosodic analysis were used to find regression formulae between automatic and perceptual assessment of four voice and four speech criteria. The regression was trained with 21 men and 62 women (average age 49.2 years) and tested with another set of 24 men and 49 women (48.3 years), all suffering from chronic hoarseness. They read the text 'Der Nordwind und die Sonne' ('The North Wind and the Sun'). Five voice and speech therapists evaluated the data on 5-point Likert scales. Ten prosodic and recognition accuracy measures (features) were identified which describe all the examined criteria. Inter-rater correlation within the expert group was between r = 0.63 for the criterion 'match of breath and sense units' and r = 0.87 for the overall voice quality. Human-machine correlation was between r = 0.40 for the match of breath and sense units and r = 0.82 for intelligibility. The perceptual ratings of different criteria were highly correlated with each other. Likewise, the feature sets modeling the criteria were very similar. The automatic method is suitable for assessing chronic hoarseness in general and for subgroups of functional and organic dysphonia. In its current version, it is almost as reliable as a randomly picked rater from a group of voice and speech therapists.

Towards Contactless Silent Speech Recognition Based on Detection of Active and Visible Articulators Using IR-UWB Radar

PubMed Central

Shin, Young Hoon; Seo, Jiwon

2016-01-01

People with hearing or speaking disabilities are deprived of the benefits of conventional speech recognition technology because it is based on acoustic signals. Recent research has focused on silent speech recognition systems that are based on the motions of a speaker’s vocal tract and articulators. Because most silent speech recognition systems use contact sensors that are very inconvenient to users or optical systems that are susceptible to environmental interference, a contactless and robust solution is hence required. Toward this objective, this paper presents a series of signal processing algorithms for a contactless silent speech recognition system using an impulse radio ultra-wide band (IR-UWB) radar. The IR-UWB radar is used to remotely and wirelessly detect motions of the lips and jaw. In order to extract the necessary features of lip and jaw motions from the received radar signals, we propose a feature extraction algorithm. The proposed algorithm noticeably improved speech recognition performance compared to the existing algorithm during our word recognition test with five speakers. We also propose a speech activity detection algorithm to automatically select speech segments from continuous input signals. Thus, speech recognition processing is performed only when speech segments are detected. Our testbed consists of commercial off-the-shelf radar products, and the proposed algorithms are readily applicable without designing specialized radar hardware for silent speech processing. PMID:27801867

Towards Contactless Silent Speech Recognition Based on Detection of Active and Visible Articulators Using IR-UWB Radar.

PubMed

Shin, Young Hoon; Seo, Jiwon

2016-10-29

People with hearing or speaking disabilities are deprived of the benefits of conventional speech recognition technology because it is based on acoustic signals. Recent research has focused on silent speech recognition systems that are based on the motions of a speaker's vocal tract and articulators. Because most silent speech recognition systems use contact sensors that are very inconvenient to users or optical systems that are susceptible to environmental interference, a contactless and robust solution is hence required. Toward this objective, this paper presents a series of signal processing algorithms for a contactless silent speech recognition system using an impulse radio ultra-wide band (IR-UWB) radar. The IR-UWB radar is used to remotely and wirelessly detect motions of the lips and jaw. In order to extract the necessary features of lip and jaw motions from the received radar signals, we propose a feature extraction algorithm. The proposed algorithm noticeably improved speech recognition performance compared to the existing algorithm during our word recognition test with five speakers. We also propose a speech activity detection algorithm to automatically select speech segments from continuous input signals. Thus, speech recognition processing is performed only when speech segments are detected. Our testbed consists of commercial off-the-shelf radar products, and the proposed algorithms are readily applicable without designing specialized radar hardware for silent speech processing.

Adaptive method of recognition of signals for one and two-frequency signal system in the telephony on the background of speech

NASA Astrophysics Data System (ADS)

Kuznetsov, Michael V.

2006-05-01

For reliable teamwork of various systems of automatic telecommunication including transferring systems of optical communication networks it is necessary authentic recognition of signals for one- or two-frequency service signal system. The analysis of time parameters of an accepted signal allows increasing reliability of detection and recognition of the service signal system on a background of speech.

User Experience of a Mobile Speaking Application with Automatic Speech Recognition for EFL Learning

ERIC Educational Resources Information Center

Ahn, Tae youn; Lee, Sangmin-Michelle

2016-01-01

With the spread of mobile devices, mobile phones have enormous potential regarding their pedagogical use in language education. The goal of this study is to analyse user experience of a mobile-based learning system that is enhanced by speech recognition technology for the improvement of EFL (English as a foreign language) learners' speaking…

EduSpeak[R]: A Speech Recognition and Pronunciation Scoring Toolkit for Computer-Aided Language Learning Applications

ERIC Educational Resources Information Center

Franco, Horacio; Bratt, Harry; Rossier, Romain; Rao Gadde, Venkata; Shriberg, Elizabeth; Abrash, Victor; Precoda, Kristin

2010-01-01

SRI International's EduSpeak[R] system is a software development toolkit that enables developers of interactive language education software to use state-of-the-art speech recognition and pronunciation scoring technology. Automatic pronunciation scoring allows the computer to provide feedback on the overall quality of pronunciation and to point to…

Presentation video retrieval using automatically recovered slide and spoken text

NASA Astrophysics Data System (ADS)

Cooper, Matthew

2013-03-01

Video is becoming a prevalent medium for e-learning. Lecture videos contain text information in both the presentation slides and lecturer's speech. This paper examines the relative utility of automatically recovered text from these sources for lecture video retrieval. To extract the visual information, we automatically detect slides within the videos and apply optical character recognition to obtain their text. Automatic speech recognition is used similarly to extract spoken text from the recorded audio. We perform controlled experiments with manually created ground truth for both the slide and spoken text from more than 60 hours of lecture video. We compare the automatically extracted slide and spoken text in terms of accuracy relative to ground truth, overlap with one another, and utility for video retrieval. Results reveal that automatically recovered slide text and spoken text contain different content with varying error profiles. Experiments demonstrate that automatically extracted slide text enables higher precision video retrieval than automatically recovered spoken text.

How should a speech recognizer work?

PubMed

Scharenborg, Odette; Norris, Dennis; Bosch, Louis; McQueen, James M

2005-11-12

Although researchers studying human speech recognition (HSR) and automatic speech recognition (ASR) share a common interest in how information processing systems (human or machine) recognize spoken language, there is little communication between the two disciplines. We suggest that this lack of communication follows largely from the fact that research in these related fields has focused on the mechanics of how speech can be recognized. In Marr's (1982) terms, emphasis has been on the algorithmic and implementational levels rather than on the computational level. In this article, we provide a computational-level analysis of the task of speech recognition, which reveals the close parallels between research concerned with HSR and ASR. We illustrate this relation by presenting a new computational model of human spoken-word recognition, built using techniques from the field of ASR that, in contrast to current existing models of HSR, recognizes words from real speech input. 2005 Lawrence Erlbaum Associates, Inc.

Specific acoustic models for spontaneous and dictated style in indonesian speech recognition

NASA Astrophysics Data System (ADS)

Vista, C. B.; Satriawan, C. H.; Lestari, D. P.; Widyantoro, D. H.

2018-03-01

The performance of an automatic speech recognition system is affected by differences in speech style between the data the model is originally trained upon and incoming speech to be recognized. In this paper, the usage of GMM-HMM acoustic models for specific speech styles is investigated. We develop two systems for the experiments; the first employs a speech style classifier to predict the speech style of incoming speech, either spontaneous or dictated, then decodes this speech using an acoustic model specifically trained for that speech style. The second system uses both acoustic models to recognise incoming speech and decides upon a final result by calculating a confidence score of decoding. Results show that training specific acoustic models for spontaneous and dictated speech styles confers a slight recognition advantage as compared to a baseline model trained on a mixture of spontaneous and dictated training data. In addition, the speech style classifier approach of the first system produced slightly more accurate results than the confidence scoring employed in the second system.

Recognition of Emotions in Mexican Spanish Speech: An Approach Based on Acoustic Modelling of Emotion-Specific Vowels

PubMed Central

Caballero-Morales, Santiago-Omar

2013-01-01

An approach for the recognition of emotions in speech is presented. The target language is Mexican Spanish, and for this purpose a speech database was created. The approach consists in the phoneme acoustic modelling of emotion-specific vowels. For this, a standard phoneme-based Automatic Speech Recognition (ASR) system was built with Hidden Markov Models (HMMs), where different phoneme HMMs were built for the consonants and emotion-specific vowels associated with four emotional states (anger, happiness, neutral, sadness). Then, estimation of the emotional state from a spoken sentence is performed by counting the number of emotion-specific vowels found in the ASR's output for the sentence. With this approach, accuracy of 87–100% was achieved for the recognition of emotional state of Mexican Spanish speech. PMID:23935410

On the recognition of emotional vocal expressions: motivations for a holistic approach.

PubMed

Esposito, Anna; Esposito, Antonietta M

2012-10-01

Human beings seem to be able to recognize emotions from speech very well and information communication technology aims to implement machines and agents that can do the same. However, to be able to automatically recognize affective states from speech signals, it is necessary to solve two main technological problems. The former concerns the identification of effective and efficient processing algorithms capable of capturing emotional acoustic features from speech sentences. The latter focuses on finding computational models able to classify, with an approximation as good as human listeners, a given set of emotional states. This paper will survey these topics and provide some insights for a holistic approach to the automatic analysis, recognition and synthesis of affective states.

Parametric Representation of the Speaker's Lips for Multimodal Sign Language and Speech Recognition

NASA Astrophysics Data System (ADS)

Ryumin, D.; Karpov, A. A.

2017-05-01

In this article, we propose a new method for parametric representation of human's lips region. The functional diagram of the method is described and implementation details with the explanation of its key stages and features are given. The results of automatic detection of the regions of interest are illustrated. A speed of the method work using several computers with different performances is reported. This universal method allows applying parametrical representation of the speaker's lipsfor the tasks of biometrics, computer vision, machine learning, and automatic recognition of face, elements of sign languages, and audio-visual speech, including lip-reading.

Assessment of voice, speech, and related quality of life in advanced head and neck cancer patients 10-years+ after chemoradiotherapy.

PubMed

Kraaijenga, S A C; Oskam, I M; van Son, R J J H; Hamming-Vrieze, O; Hilgers, F J M; van den Brekel, M W M; van der Molen, L

2016-04-01

Assessment of long-term objective and subjective voice, speech, articulation, and quality of life in patients with head and neck cancer (HNC) treated with concurrent chemoradiotherapy (CRT) for advanced, stage IV disease. Twenty-two disease-free survivors, treated with cisplatin-based CRT for inoperable HNC (1999-2004), were evaluated at 10-years post-treatment. A standard Dutch text was recorded. Perceptual analysis of voice, speech, and articulation was conducted by two expert listeners (SLPs). Also an experimental expert system based on automatic speech recognition was used. Patients' perception of voice and speech and related quality of life was assessed with the Voice Handicap Index (VHI) and Speech Handicap Index (SHI) questionnaires. At a median follow-up of 11-years, perceptual evaluation showed abnormal scores in up to 64% of cases, depending on the outcome parameter analyzed. Automatic assessment of voice and speech parameters correlated moderate to strong with perceptual outcome scores. Patient-reported problems with voice (VHI>15) and speech (SHI>6) in daily life were present in 68% and 77% of patients, respectively. Patients treated with IMRT showed significantly less impairment compared to those treated with conventional radiotherapy. More than 10-years after organ-preservation treatment, voice and speech problems are common in this patient cohort, as assessed with perceptual evaluation, automatic speech recognition, and with validated structured questionnaires. There were fewer complaints in patients treated with IMRT than with conventional radiotherapy. Copyright © 2016 Elsevier Ltd. All rights reserved.

The influence of age, hearing, and working memory on the speech comprehension benefit derived from an automatic speech recognition system.

PubMed

Zekveld, Adriana A; Kramer, Sophia E; Kessens, Judith M; Vlaming, Marcel S M G; Houtgast, Tammo

2009-04-01

The aim of the current study was to examine whether partly incorrect subtitles that are automatically generated by an Automatic Speech Recognition (ASR) system, improve speech comprehension by listeners with hearing impairment. In an earlier study (Zekveld et al. 2008), we showed that speech comprehension in noise by young listeners with normal hearing improves when presenting partly incorrect, automatically generated subtitles. The current study focused on the effects of age, hearing loss, visual working memory capacity, and linguistic skills on the benefit obtained from automatically generated subtitles during listening to speech in noise. In order to investigate the effects of age and hearing loss, three groups of participants were included: 22 young persons with normal hearing (YNH, mean age = 21 years), 22 middle-aged adults with normal hearing (MA-NH, mean age = 55 years) and 30 middle-aged adults with hearing impairment (MA-HI, mean age = 57 years). The benefit from automatic subtitling was measured by Speech Reception Threshold (SRT) tests (Plomp & Mimpen, 1979). Both unimodal auditory and bimodal audiovisual SRT tests were performed. In the audiovisual tests, the subtitles were presented simultaneously with the speech, whereas in the auditory test, only speech was presented. The difference between the auditory and audiovisual SRT was defined as the audiovisual benefit. Participants additionally rated the listening effort. We examined the influences of ASR accuracy level and text delay on the audiovisual benefit and the listening effort using a repeated measures General Linear Model analysis. In a correlation analysis, we evaluated the relationships between age, auditory SRT, visual working memory capacity and the audiovisual benefit and listening effort. The automatically generated subtitles improved speech comprehension in noise for all ASR accuracies and delays covered by the current study. Higher ASR accuracy levels resulted in more benefit obtained from the subtitles. Speech comprehension improved even for relatively low ASR accuracy levels; for example, participants obtained about 2 dB SNR audiovisual benefit for ASR accuracies around 74%. Delaying the presentation of the text reduced the benefit and increased the listening effort. Participants with relatively low unimodal speech comprehension obtained greater benefit from the subtitles than participants with better unimodal speech comprehension. We observed an age-related decline in the working-memory capacity of the listeners with normal hearing. A higher age and a lower working memory capacity were associated with increased effort required to use the subtitles to improve speech comprehension. Participants were able to use partly incorrect and delayed subtitles to increase their comprehension of speech in noise, regardless of age and hearing loss. This supports the further development and evaluation of an assistive listening system that displays automatically recognized speech to aid speech comprehension by listeners with hearing impairment.

Strategies for distant speech recognitionin reverberant environments

NASA Astrophysics Data System (ADS)

Delcroix, Marc; Yoshioka, Takuya; Ogawa, Atsunori; Kubo, Yotaro; Fujimoto, Masakiyo; Ito, Nobutaka; Kinoshita, Keisuke; Espi, Miquel; Araki, Shoko; Hori, Takaaki; Nakatani, Tomohiro

2015-12-01

Reverberation and noise are known to severely affect the automatic speech recognition (ASR) performance of speech recorded by distant microphones. Therefore, we must deal with reverberation if we are to realize high-performance hands-free speech recognition. In this paper, we review a recognition system that we developed at our laboratory to deal with reverberant speech. The system consists of a speech enhancement (SE) front-end that employs long-term linear prediction-based dereverberation followed by noise reduction. We combine our SE front-end with an ASR back-end that uses neural networks for acoustic and language modeling. The proposed system achieved top scores on the ASR task of the REVERB challenge. This paper describes the different technologies used in our system and presents detailed experimental results that justify our implementation choices and may provide hints for designing distant ASR systems.

Speech recognition systems on the Cell Broadband Engine

DOE Office of Scientific and Technical Information (OSTI.GOV)

Liu, Y; Jones, H; Vaidya, S

In this paper we describe our design, implementation, and first results of a prototype connected-phoneme-based speech recognition system on the Cell Broadband Engine{trademark} (Cell/B.E.). Automatic speech recognition decodes speech samples into plain text (other representations are possible) and must process samples at real-time rates. Fortunately, the computational tasks involved in this pipeline are highly data-parallel and can receive significant hardware acceleration from vector-streaming architectures such as the Cell/B.E. Identifying and exploiting these parallelism opportunities is challenging, but also critical to improving system performance. We observed, from our initial performance timings, that a single Cell/B.E. processor can recognize speech from thousandsmore » of simultaneous voice channels in real time--a channel density that is orders-of-magnitude greater than the capacity of existing software speech recognizers based on CPUs (central processing units). This result emphasizes the potential for Cell/B.E.-based speech recognition and will likely lead to the future development of production speech systems using Cell/B.E. clusters.« less

Recognizing Whispered Speech Produced by an Individual with Surgically Reconstructed Larynx Using Articulatory Movement Data

PubMed Central

Cao, Beiming; Kim, Myungjong; Mau, Ted; Wang, Jun

2017-01-01

Individuals with larynx (vocal folds) impaired have problems in controlling their glottal vibration, producing whispered speech with extreme hoarseness. Standard automatic speech recognition using only acoustic cues is typically ineffective for whispered speech because the corresponding spectral characteristics are distorted. Articulatory cues such as the tongue and lip motion may help in recognizing whispered speech since articulatory motion patterns are generally not affected. In this paper, we investigated whispered speech recognition for patients with reconstructed larynx using articulatory movement data. A data set with both acoustic and articulatory motion data was collected from a patient with surgically reconstructed larynx using an electromagnetic articulograph. Two speech recognition systems, Gaussian mixture model-hidden Markov model (GMM-HMM) and deep neural network-HMM (DNN-HMM), were used in the experiments. Experimental results showed adding either tongue or lip motion data to acoustic features such as mel-frequency cepstral coefficient (MFCC) significantly reduced the phone error rates on both speech recognition systems. Adding both tongue and lip data achieved the best performance. PMID:29423453

Automatic Speech Acquisition and Recognition for Spacesuit Audio Systems

NASA Technical Reports Server (NTRS)

Ye, Sherry

2015-01-01

NASA has a widely recognized but unmet need for novel human-machine interface technologies that can facilitate communication during astronaut extravehicular activities (EVAs), when loud noises and strong reverberations inside spacesuits make communication challenging. WeVoice, Inc., has developed a multichannel signal-processing method for speech acquisition in noisy and reverberant environments that enables automatic speech recognition (ASR) technology inside spacesuits. The technology reduces noise by exploiting differences between the statistical nature of signals (i.e., speech) and noise that exists in the spatial and temporal domains. As a result, ASR accuracy can be improved to the level at which crewmembers will find the speech interface useful. System components and features include beam forming/multichannel noise reduction, single-channel noise reduction, speech feature extraction, feature transformation and normalization, feature compression, and ASR decoding. Arithmetic complexity models were developed and will help designers of real-time ASR systems select proper tasks when confronted with constraints in computational resources. In Phase I of the project, WeVoice validated the technology. The company further refined the technology in Phase II and developed a prototype for testing and use by suited astronauts.

Automatic Speech Recognition in Air Traffic Control: a Human Factors Perspective

NASA Technical Reports Server (NTRS)

Karlsson, Joakim

1990-01-01

The introduction of Automatic Speech Recognition (ASR) technology into the Air Traffic Control (ATC) system has the potential to improve overall safety and efficiency. However, because ASR technology is inherently a part of the man-machine interface between the user and the system, the human factors issues involved must be addressed. Here, some of the human factors problems are identified and related methods of investigation are presented. Research at M.I.T.'s Flight Transportation Laboratory is being conducted from a human factors perspective, focusing on intelligent parser design, presentation of feedback, error correction strategy design, and optimal choice of input modalities.

Random Deep Belief Networks for Recognizing Emotions from Speech Signals.

PubMed

Wen, Guihua; Li, Huihui; Huang, Jubing; Li, Danyang; Xun, Eryang

2017-01-01

Now the human emotions can be recognized from speech signals using machine learning methods; however, they are challenged by the lower recognition accuracies in real applications due to lack of the rich representation ability. Deep belief networks (DBN) can automatically discover the multiple levels of representations in speech signals. To make full of its advantages, this paper presents an ensemble of random deep belief networks (RDBN) method for speech emotion recognition. It firstly extracts the low level features of the input speech signal and then applies them to construct lots of random subspaces. Each random subspace is then provided for DBN to yield the higher level features as the input of the classifier to output an emotion label. All outputted emotion labels are then fused through the majority voting to decide the final emotion label for the input speech signal. The conducted experimental results on benchmark speech emotion databases show that RDBN has better accuracy than the compared methods for speech emotion recognition.

Random Deep Belief Networks for Recognizing Emotions from Speech Signals

PubMed Central

Li, Huihui; Huang, Jubing; Li, Danyang; Xun, Eryang

2017-01-01

Now the human emotions can be recognized from speech signals using machine learning methods; however, they are challenged by the lower recognition accuracies in real applications due to lack of the rich representation ability. Deep belief networks (DBN) can automatically discover the multiple levels of representations in speech signals. To make full of its advantages, this paper presents an ensemble of random deep belief networks (RDBN) method for speech emotion recognition. It firstly extracts the low level features of the input speech signal and then applies them to construct lots of random subspaces. Each random subspace is then provided for DBN to yield the higher level features as the input of the classifier to output an emotion label. All outputted emotion labels are then fused through the majority voting to decide the final emotion label for the input speech signal. The conducted experimental results on benchmark speech emotion databases show that RDBN has better accuracy than the compared methods for speech emotion recognition. PMID:28356908

Hidden Markov models in automatic speech recognition

NASA Astrophysics Data System (ADS)

Wrzoskowicz, Adam

1993-11-01

This article describes a method for constructing an automatic speech recognition system based on hidden Markov models (HMMs). The author discusses the basic concepts of HMM theory and the application of these models to the analysis and recognition of speech signals. The author provides algorithms which make it possible to train the ASR system and recognize signals on the basis of distinct stochastic models of selected speech sound classes. The author describes the specific components of the system and the procedures used to model and recognize speech. The author discusses problems associated with the choice of optimal signal detection and parameterization characteristics and their effect on the performance of the system. The author presents different options for the choice of speech signal segments and their consequences for the ASR process. The author gives special attention to the use of lexical, syntactic, and semantic information for the purpose of improving the quality and efficiency of the system. The author also describes an ASR system developed by the Speech Acoustics Laboratory of the IBPT PAS. The author discusses the results of experiments on the effect of noise on the performance of the ASR system and describes methods of constructing HMM's designed to operate in a noisy environment. The author also describes a language for human-robot communications which was defined as a complex multilevel network from an HMM model of speech sounds geared towards Polish inflections. The author also added mandatory lexical and syntactic rules to the system for its communications vocabulary.

Performance of Automated Speech Scoring on Different Low- to Medium-Entropy Item Types for Low-Proficiency English Learners. Research Report. ETS RR-17-12

ERIC Educational Resources Information Center

Loukina, Anastassia; Zechner, Klaus; Yoon, Su-Youn; Zhang, Mo; Tao, Jidong; Wang, Xinhao; Lee, Chong Min; Mulholland, Matthew

2017-01-01

This report presents an overview of the "SpeechRater"? automated scoring engine model building and evaluation process for several item types with a focus on a low-English-proficiency test-taker population. We discuss each stage of speech scoring, including automatic speech recognition, filtering models for nonscorable responses, and…

Computational Modeling of Emotions and Affect in Social-Cultural Interaction

DTIC Science & Technology

2013-10-02

acoustic and textual information sources. Second, a cross-lingual study was performed that shed light on how human perception and automatic recognition...speech is produced, a speaker’s pitch and intonational pattern, and word usage. Better feature representation and advanced approaches were used to...recognition performance, and improved our understanding of language/cultural impact on human perception of emotion and automatic classification. • Units

Automatic Intention Recognition in Conversation Processing

ERIC Educational Resources Information Center

Holtgraves, Thomas

2008-01-01

A fundamental assumption of many theories of conversation is that comprehension of a speaker's utterance involves recognition of the speaker's intention in producing that remark. However, the nature of intention recognition is not clear. One approach is to conceptualize a speaker's intention in terms of speech acts [Searle, J. (1969). "Speech…

[The endpoint detection of cough signal in continuous speech].

PubMed

Yang, Guoqing; Mo, Hongqiang; Li, Wen; Lian, Lianfang; Zheng, Zeguang

2010-06-01

The endpoint detection of cough signal in continuous speech has been researched in order to improve the efficiency and veracity of manual recognition or computer-based automatic recognition. First, using the short time zero crossing ratio(ZCR) for identifying the suspicious coughs and getting the threshold of short time energy based on acoustic characteristics of cough. Then, the short time energy is combined with short time ZCR in order to implement the endpoint detection of cough in continuous speech. To evaluate the effect of the method, first, the virtual number of coughs in each recording was identified by two experienced doctors using the graphical user interface (GUI). Second, the recordings were analyzed by automatic endpoint detection program under Matlab7.0. Finally, the comparison between these two results showed: The error rate of undetected cough is 2.18%, and 98.13% of noise, silence and speech were removed. The way of setting short time energy threshold is robust. The endpoint detection program can remove most speech and noise, thus maintaining a lower rate of error.

Massively-Parallel Architectures for Automatic Recognition of Visual Speech Signals

DTIC Science & Technology

1988-10-12

Secusrity Clamifieation, Nlassively-Parallel Architectures for Automa ic Recognitio of Visua, Speech Signals 12. PERSONAL AUTHOR(S) Terrence J...characteristics of speech from tJhe, visual speech signals. Neural networks have been trained on a database of vowels. The rqw images of faces , aligned and...images of faces , aligned and preprocessed, were used as input to these network which were trained to estimate the corresponding envelope of the

Speech Acquisition and Automatic Speech Recognition for Integrated Spacesuit Audio Systems

NASA Technical Reports Server (NTRS)

Huang, Yiteng; Chen, Jingdong; Chen, Shaoyan

2010-01-01

A voice-command human-machine interface system has been developed for spacesuit extravehicular activity (EVA) missions. A multichannel acoustic signal processing method has been created for distant speech acquisition in noisy and reverberant environments. This technology reduces noise by exploiting differences in the statistical nature of signal (i.e., speech) and noise that exists in the spatial and temporal domains. As a result, the automatic speech recognition (ASR) accuracy can be improved to the level at which crewmembers would find the speech interface useful. The developed speech human/machine interface will enable both crewmember usability and operational efficiency. It can enjoy a fast rate of data/text entry, small overall size, and can be lightweight. In addition, this design will free the hands and eyes of a suited crewmember. The system components and steps include beam forming/multi-channel noise reduction, single-channel noise reduction, speech feature extraction, feature transformation and normalization, feature compression, model adaption, ASR HMM (Hidden Markov Model) training, and ASR decoding. A state-of-the-art phoneme recognizer can obtain an accuracy rate of 65 percent when the training and testing data are free of noise. When it is used in spacesuits, the rate drops to about 33 percent. With the developed microphone array speech-processing technologies, the performance is improved and the phoneme recognition accuracy rate rises to 44 percent. The recognizer can be further improved by combining the microphone array and HMM model adaptation techniques and using speech samples collected from inside spacesuits. In addition, arithmetic complexity models for the major HMMbased ASR components were developed. They can help real-time ASR system designers select proper tasks when in the face of constraints in computational resources.

Automatic speech recognition and training for severely dysarthric users of assistive technology: the STARDUST project.

PubMed

Parker, Mark; Cunningham, Stuart; Enderby, Pam; Hawley, Mark; Green, Phil

2006-01-01

The STARDUST project developed robust computer speech recognizers for use by eight people with severe dysarthria and concomitant physical disability to access assistive technologies. Independent computer speech recognizers trained with normal speech are of limited functional use by those with severe dysarthria due to limited and inconsistent proximity to "normal" articulatory patterns. Severe dysarthric output may also be characterized by a small mass of distinguishable phonetic tokens making the acoustic differentiation of target words difficult. Speaker dependent computer speech recognition using Hidden Markov Models was achieved by the identification of robust phonetic elements within the individual speaker output patterns. A new system of speech training using computer generated visual and auditory feedback reduced the inconsistent production of key phonetic tokens over time.

Automatic translation among spoken languages

NASA Technical Reports Server (NTRS)

Walter, Sharon M.; Costigan, Kelly

1994-01-01

The Machine Aided Voice Translation (MAVT) system was developed in response to the shortage of experienced military field interrogators with both foreign language proficiency and interrogation skills. Combining speech recognition, machine translation, and speech generation technologies, the MAVT accepts an interrogator's spoken English question and translates it into spoken Spanish. The spoken Spanish response of the potential informant can then be translated into spoken English. Potential military and civilian applications for automatic spoken language translation technology are discussed in this paper.

Call recognition and individual identification of fish vocalizations based on automatic speech recognition: An example with the Lusitanian toadfish.

PubMed

Vieira, Manuel; Fonseca, Paulo J; Amorim, M Clara P; Teixeira, Carlos J C

2015-12-01

The study of acoustic communication in animals often requires not only the recognition of species specific acoustic signals but also the identification of individual subjects, all in a complex acoustic background. Moreover, when very long recordings are to be analyzed, automatic recognition and identification processes are invaluable tools to extract the relevant biological information. A pattern recognition methodology based on hidden Markov models is presented inspired by successful results obtained in the most widely known and complex acoustical communication signal: human speech. This methodology was applied here for the first time to the detection and recognition of fish acoustic signals, specifically in a stream of round-the-clock recordings of Lusitanian toadfish (Halobatrachus didactylus) in their natural estuarine habitat. The results show that this methodology is able not only to detect the mating sounds (boatwhistles) but also to identify individual male toadfish, reaching an identification rate of ca. 95%. Moreover this method also proved to be a powerful tool to assess signal durations in large data sets. However, the system failed in recognizing other sound types.

Auditory models for speech analysis

NASA Astrophysics Data System (ADS)

Maybury, Mark T.

This paper reviews the psychophysical basis for auditory models and discusses their application to automatic speech recognition. First an overview of the human auditory system is presented, followed by a review of current knowledge gleaned from neurological and psychoacoustic experimentation. Next, a general framework describes established peripheral auditory models which are based on well-understood properties of the peripheral auditory system. This is followed by a discussion of current enhancements to that models to include nonlinearities and synchrony information as well as other higher auditory functions. Finally, the initial performance of auditory models in the task of speech recognition is examined and additional applications are mentioned.

The Development of the Speaker Independent ARM Continuous Speech Recognition System

DTIC Science & Technology

1992-01-01

spokeTi airborne reconnaissance reports u-ing a speech recognition system based on phoneme-level hidden Markov models (HMMs). Previous versions of the ARM...will involve automatic selection from multiple model sets, corresponding to different speaker types, and that the most rudimen- tary partition of a...The vocabulary size for the ARM task is 497 words. These words are related to the phoneme-level symbols corresponding to the models in the model set

Stochastic Modeling as a Means of Automatic Speech Recognition

DTIC Science & Technology

1975-04-01

companng ihc features of different speech recognition systems, attention is often focused on thc control structures and the methods o’ communication...with no need to use secondary storage . Note that we go from a group of separate knowledge sources to an integrated network representation in...exhaust the available lime or storage . - - - . . 1- .-.-.. mmm^~ i — ■ ■ ’ ■ C haplcr I - IN I ROÜliCl ION Page 13 On the other hand

Automatically Detecting Likely Edits in Clinical Notes Created Using Automatic Speech Recognition

PubMed Central

Lybarger, Kevin; Ostendorf, Mari; Yetisgen, Meliha

2017-01-01

The use of automatic speech recognition (ASR) to create clinical notes has the potential to reduce costs associated with note creation for electronic medical records, but at current system accuracy levels, post-editing by practitioners is needed to ensure note quality. Aiming to reduce the time required to edit ASR transcripts, this paper investigates novel methods for automatic detection of edit regions within the transcripts, including both putative ASR errors but also regions that are targets for cleanup or rephrasing. We create detection models using logistic regression and conditional random field models, exploring a variety of text-based features that consider the structure of clinical notes and exploit the medical context. Different medical text resources are used to improve feature extraction. Experimental results on a large corpus of practitioner-edited clinical notes show that 67% of sentence-level edits and 45% of word-level edits can be detected with a false detection rate of 15%. PMID:29854187

A speech-controlled environmental control system for people with severe dysarthria.

PubMed

Hawley, Mark S; Enderby, Pam; Green, Phil; Cunningham, Stuart; Brownsell, Simon; Carmichael, James; Parker, Mark; Hatzis, Athanassios; O'Neill, Peter; Palmer, Rebecca

2007-06-01

Automatic speech recognition (ASR) can provide a rapid means of controlling electronic assistive technology. Off-the-shelf ASR systems function poorly for users with severe dysarthria because of the increased variability of their articulations. We have developed a limited vocabulary speaker dependent speech recognition application which has greater tolerance to variability of speech, coupled with a computerised training package which assists dysarthric speakers to improve the consistency of their vocalisations and provides more data for recogniser training. These applications, and their implementation as the interface for a speech-controlled environmental control system (ECS), are described. The results of field trials to evaluate the training program and the speech-controlled ECS are presented. The user-training phase increased the recognition rate from 88.5% to 95.4% (p<0.001). Recognition rates were good for people with even the most severe dysarthria in everyday usage in the home (mean word recognition rate 86.9%). Speech-controlled ECS were less accurate (mean task completion accuracy 78.6% versus 94.8%) but were faster to use than switch-scanning systems, even taking into account the need to repeat unsuccessful operations (mean task completion time 7.7s versus 16.9s, p<0.001). It is concluded that a speech-controlled ECS is a viable alternative to switch-scanning systems for some people with severe dysarthria and would lead, in many cases, to more efficient control of the home.

The Mechanical Recognition of Speech: Prospects for Use in the Teaching of Languages.

ERIC Educational Resources Information Center

Pulliam, Robert

1970-01-01

This paper begins with a brief account of the development of automatic speech recogniton (ASR) and then proceeds to an examination of ASR systems typical of the kind now in operation. It is stressed that such systems, although highly developed, do not recognize speech in the same sense as the human being does, and that they can not deal with a…

Speech recognition-based and automaticity programs to help students with severe reading and spelling problems.

PubMed

Higgins, Eleanor L; Raskind, Marshall H

2004-12-01

This study was conducted to assess the effectiveness of two programs developed by the Frostig Center Research Department to improve the reading and spelling of students with learning disabilities (LD): a computer Speech Recognition-based Program (SRBP) and a computer and text-based Automaticity Program (AP). Twenty-eight LD students with reading and spelling difficulties (aged 8 to 18) received each program for 17 weeks and were compared with 16 students in a contrast group who did not receive either program. After adjusting for age and IQ, both the SRBP and AP groups showed significant differences over the contrast group in improving word recognition and reading comprehension. Neither program showed significant differences over contrasts in spelling. The SRBP also improved the performance of the target group when compared with the contrast group on phonological elision and nonword reading efficiency tasks. The AP showed significant differences in all process and reading efficiency measures.

Four-Channel Biosignal Analysis and Feature Extraction for Automatic Emotion Recognition

NASA Astrophysics Data System (ADS)

Kim, Jonghwa; André, Elisabeth

This paper investigates the potential of physiological signals as a reliable channel for automatic recognition of user's emotial state. For the emotion recognition, little attention has been paid so far to physiological signals compared to audio-visual emotion channels such as facial expression or speech. All essential stages of automatic recognition system using biosignals are discussed, from recording physiological dataset up to feature-based multiclass classification. Four-channel biosensors are used to measure electromyogram, electrocardiogram, skin conductivity and respiration changes. A wide range of physiological features from various analysis domains, including time/frequency, entropy, geometric analysis, subband spectra, multiscale entropy, etc., is proposed in order to search the best emotion-relevant features and to correlate them with emotional states. The best features extracted are specified in detail and their effectiveness is proven by emotion recognition results.

Robust Recognition of Loud and Lombard speech in the Fighter Cockpit Environment

DTIC Science & Technology

1988-08-01

the latter as inter-speaker variability. According to Zue [Z85j, inter-speaker variabilities can be attributed to sociolinguistic background, dialect...34 Journal of the Acoustical Society of America , Vol 50, 1971. [At74I B. S. Atal, "Linear prediction for speaker identification," Journal of the Acoustical...Society of America , Vol 55, 1974. [B771 B. Beek, E. P. Neuberg, and D. C. Hodge, "An Assessment of the Technology of Automatic Speech Recognition for

Development of coffee maker service robot using speech and face recognition systems using POMDP

NASA Astrophysics Data System (ADS)

Budiharto, Widodo; Meiliana; Santoso Gunawan, Alexander Agung

2016-07-01

There are many development of intelligent service robot in order to interact with user naturally. This purpose can be done by embedding speech and face recognition ability on specific tasks to the robot. In this research, we would like to propose Intelligent Coffee Maker Robot which the speech recognition is based on Indonesian language and powered by statistical dialogue systems. This kind of robot can be used in the office, supermarket or restaurant. In our scenario, robot will recognize user's face and then accept commands from the user to do an action, specifically in making a coffee. Based on our previous work, the accuracy for speech recognition is about 86% and face recognition is about 93% in laboratory experiments. The main problem in here is to know the intention of user about how sweetness of the coffee. The intelligent coffee maker robot should conclude the user intention through conversation under unreliable automatic speech in noisy environment. In this paper, this spoken dialog problem is treated as a partially observable Markov decision process (POMDP). We describe how this formulation establish a promising framework by empirical results. The dialog simulations are presented which demonstrate significant quantitative outcome.

Studies in automatic speech recognition and its application in aerospace

NASA Astrophysics Data System (ADS)

Taylor, Michael Robinson

Human communication is characterized in terms of the spectral and temporal dimensions of speech waveforms. Electronic speech recognition strategies based on Dynamic Time Warping and Markov Model algorithms are described and typical digit recognition error rates are tabulated. The application of Direct Voice Input (DVI) as an interface between man and machine is explored within the context of civil and military aerospace programmes. Sources of physical and emotional stress affecting speech production within military high performance aircraft are identified. Experimental results are reported which quantify fundamental frequency and coarse temporal dimensions of male speech as a function of the vibration, linear acceleration and noise levels typical of aerospace environments; preliminary indications of acoustic phonetic variability reported by other researchers are summarized. Connected whole-word pattern recognition error rates are presented for digits spoken under controlled Gz sinusoidal whole-body vibration. Correlations are made between significant increases in recognition error rate and resonance of the abdomen-thorax and head subsystems of the body. The phenomenon of vibrato style speech produced under low frequency whole-body Gz vibration is also examined. Interactive DVI system architectures and avionic data bus integration concepts are outlined together with design procedures for the efficient development of pilot-vehicle command and control protocols.

Thai Automatic Speech Recognition

DTIC Science & Technology

2005-01-01

used in an external DARPA evaluation involving medical scenarios between an American Doctor and a naïve monolingual Thai patient. 2. Thai Language... dictionary generation more challenging, and (3) the lack of word segmentation, which calls for automatic segmentation approaches to make n-gram language...requires a dictionary and provides various segmentation algorithms to automatically select suitable segmentations. Here we used a maximal matching

A novel probabilistic framework for event-based speech recognition

NASA Astrophysics Data System (ADS)

Juneja, Amit; Espy-Wilson, Carol

2003-10-01

One of the reasons for unsatisfactory performance of the state-of-the-art automatic speech recognition (ASR) systems is the inferior acoustic modeling of low-level acoustic-phonetic information in the speech signal. An acoustic-phonetic approach to ASR, on the other hand, explicitly targets linguistic information in the speech signal, but such a system for continuous speech recognition (CSR) is not known to exist. A probabilistic and statistical framework for CSR based on the idea of the representation of speech sounds by bundles of binary valued articulatory phonetic features is proposed. Multiple probabilistic sequences of linguistically motivated landmarks are obtained using binary classifiers of manner phonetic features-syllabic, sonorant and continuant-and the knowledge-based acoustic parameters (APs) that are acoustic correlates of those features. The landmarks are then used for the extraction of knowledge-based APs for source and place phonetic features and their binary classification. Probabilistic landmark sequences are constrained using manner class language models for isolated or connected word recognition. The proposed method could overcome the disadvantages encountered by the early acoustic-phonetic knowledge-based systems that led the ASR community to switch to systems highly dependent on statistical pattern analysis methods and probabilistic language or grammar models.

The Promise of NLP and Speech Processing Technologies in Language Assessment

ERIC Educational Resources Information Center

Chapelle, Carol A.; Chung, Yoo-Ree

2010-01-01

Advances in natural language processing (NLP) and automatic speech recognition and processing technologies offer new opportunities for language testing. Despite their potential uses on a range of language test item types, relatively little work has been done in this area, and it is therefore not well understood by test developers, researchers or…

Validation of Automated Scoring of Oral Reading

ERIC Educational Resources Information Center

Balogh, Jennifer; Bernstein, Jared; Cheng, Jian; Van Moere, Alistair; Townshend, Brent; Suzuki, Masanori

2012-01-01

A two-part experiment is presented that validates a new measurement tool for scoring oral reading ability. Data collected by the U.S. government in a large-scale literacy assessment of adults were analyzed by a system called VersaReader that uses automatic speech recognition and speech processing technologies to score oral reading fluency. In the…

Voice Interactive Analysis System Study. Final Report, August 28, 1978 through March 23, 1979.

ERIC Educational Resources Information Center

Harry, D. P.; And Others

The Voice Interactive Analysis System study continued research and development of the LISTEN real-time, minicomputer based connected speech recognition system, within NAVTRAEQUIPCEN'S program of developing automatic speech technology in support of training. An attempt was made to identify the most effective features detected by the TTI-500 model…

Speaker emotion recognition: from classical classifiers to deep neural networks

NASA Astrophysics Data System (ADS)

Mezghani, Eya; Charfeddine, Maha; Nicolas, Henri; Ben Amar, Chokri

2018-04-01

Speaker emotion recognition is considered among the most challenging tasks in recent years. In fact, automatic systems for security, medicine or education can be improved when considering the speech affective state. In this paper, a twofold approach for speech emotion classification is proposed. At the first side, a relevant set of features is adopted, and then at the second one, numerous supervised training techniques, involving classic methods as well as deep learning, are experimented. Experimental results indicate that deep architecture can improve classification performance on two affective databases, the Berlin Dataset of Emotional Speech and the SAVEE Dataset Surrey Audio-Visual Expressed Emotion.

Neural speech recognition: continuous phoneme decoding using spatiotemporal representations of human cortical activity

NASA Astrophysics Data System (ADS)

Moses, David A.; Mesgarani, Nima; Leonard, Matthew K.; Chang, Edward F.

2016-10-01

Objective. The superior temporal gyrus (STG) and neighboring brain regions play a key role in human language processing. Previous studies have attempted to reconstruct speech information from brain activity in the STG, but few of them incorporate the probabilistic framework and engineering methodology used in modern speech recognition systems. In this work, we describe the initial efforts toward the design of a neural speech recognition (NSR) system that performs continuous phoneme recognition on English stimuli with arbitrary vocabulary sizes using the high gamma band power of local field potentials in the STG and neighboring cortical areas obtained via electrocorticography. Approach. The system implements a Viterbi decoder that incorporates phoneme likelihood estimates from a linear discriminant analysis model and transition probabilities from an n-gram phonemic language model. Grid searches were used in an attempt to determine optimal parameterizations of the feature vectors and Viterbi decoder. Main results. The performance of the system was significantly improved by using spatiotemporal representations of the neural activity (as opposed to purely spatial representations) and by including language modeling and Viterbi decoding in the NSR system. Significance. These results emphasize the importance of modeling the temporal dynamics of neural responses when analyzing their variations with respect to varying stimuli and demonstrate that speech recognition techniques can be successfully leveraged when decoding speech from neural signals. Guided by the results detailed in this work, further development of the NSR system could have applications in the fields of automatic speech recognition and neural prosthetics.

Analysis of Factors Affecting System Performance in the ASpIRE Challenge

DTIC Science & Technology

2015-12-13

performance in the ASpIRE (Automatic Speech recognition In Reverberant Environments) challenge. In particular, overall word error rate (WER) of the solver...systems is analyzed as a function of room, distance between talker and microphone, and microphone type. We also analyze speech activity detection...analysis will inform the design of future challenges and provide insight into the efficacy of current solutions addressing noisy reverberant speech

Automatic Speech Recognition Predicts Speech Intelligibility and Comprehension for Listeners With Simulated Age-Related Hearing Loss.

PubMed

Fontan, Lionel; Ferrané, Isabelle; Farinas, Jérôme; Pinquier, Julien; Tardieu, Julien; Magnen, Cynthia; Gaillard, Pascal; Aumont, Xavier; Füllgrabe, Christian

2017-09-18

The purpose of this article is to assess speech processing for listeners with simulated age-related hearing loss (ARHL) and to investigate whether the observed performance can be replicated using an automatic speech recognition (ASR) system. The long-term goal of this research is to develop a system that will assist audiologists/hearing-aid dispensers in the fine-tuning of hearing aids. Sixty young participants with normal hearing listened to speech materials mimicking the perceptual consequences of ARHL at different levels of severity. Two intelligibility tests (repetition of words and sentences) and 1 comprehension test (responding to oral commands by moving virtual objects) were administered. Several language models were developed and used by the ASR system in order to fit human performances. Strong significant positive correlations were observed between human and ASR scores, with coefficients up to .99. However, the spectral smearing used to simulate losses in frequency selectivity caused larger declines in ASR performance than in human performance. Both intelligibility and comprehension scores for listeners with simulated ARHL are highly correlated with the performances of an ASR-based system. In the future, it needs to be determined if the ASR system is similarly successful in predicting speech processing in noise and by older people with ARHL.

Visual speech influences speech perception immediately but not automatically.

PubMed

Mitterer, Holger; Reinisch, Eva

2017-02-01

Two experiments examined the time course of the use of auditory and visual speech cues to spoken word recognition using an eye-tracking paradigm. Results of the first experiment showed that the use of visual speech cues from lipreading is reduced if concurrently presented pictures require a division of attentional resources. This reduction was evident even when listeners' eye gaze was on the speaker rather than the (static) pictures. Experiment 2 used a deictic hand gesture to foster attention to the speaker. At the same time, the visual processing load was reduced by keeping the visual display constant over a fixed number of successive trials. Under these conditions, the visual speech cues from lipreading were used. Moreover, the eye-tracking data indicated that visual information was used immediately and even earlier than auditory information. In combination, these data indicate that visual speech cues are not used automatically, but if they are used, they are used immediately.

Approximated mutual information training for speech recognition using myoelectric signals.

PubMed

Guo, Hua J; Chan, A D C

2006-01-01

A new training algorithm called the approximated maximum mutual information (AMMI) is proposed to improve the accuracy of myoelectric speech recognition using hidden Markov models (HMMs). Previous studies have demonstrated that automatic speech recognition can be performed using myoelectric signals from articulatory muscles of the face. Classification of facial myoelectric signals can be performed using HMMs that are trained using the maximum likelihood (ML) algorithm; however, this algorithm maximizes the likelihood of the observations in the training sequence, which is not directly associated with optimal classification accuracy. The AMMI training algorithm attempts to maximize the mutual information, thereby training the HMMs to optimize their parameters for discrimination. Our results show that AMMI training consistently reduces the error rates compared to these by the ML training, increasing the accuracy by approximately 3% on average.

Human phoneme recognition depending on speech-intrinsic variability.

PubMed

Meyer, Bernd T; Jürgens, Tim; Wesker, Thorsten; Brand, Thomas; Kollmeier, Birger

2010-11-01

The influence of different sources of speech-intrinsic variation (speaking rate, effort, style and dialect or accent) on human speech perception was investigated. In listening experiments with 16 listeners, confusions of consonant-vowel-consonant (CVC) and vowel-consonant-vowel (VCV) sounds in speech-weighted noise were analyzed. Experiments were based on the OLLO logatome speech database, which was designed for a man-machine comparison. It contains utterances spoken by 50 speakers from five dialect/accent regions and covers several intrinsic variations. By comparing results depending on intrinsic and extrinsic variations (i.e., different levels of masking noise), the degradation induced by variabilities can be expressed in terms of the SNR. The spectral level distance between the respective speech segment and the long-term spectrum of the masking noise was found to be a good predictor for recognition rates, while phoneme confusions were influenced by the distance to spectrally close phonemes. An analysis based on transmitted information of articulatory features showed that voicing and manner of articulation are comparatively robust cues in the presence of intrinsic variations, whereas the coding of place is more degraded. The database and detailed results have been made available for comparisons between human speech recognition (HSR) and automatic speech recognizers (ASR).

A voice-input voice-output communication aid for people with severe speech impairment.

PubMed

Hawley, Mark S; Cunningham, Stuart P; Green, Phil D; Enderby, Pam; Palmer, Rebecca; Sehgal, Siddharth; O'Neill, Peter

2013-01-01

A new form of augmentative and alternative communication (AAC) device for people with severe speech impairment-the voice-input voice-output communication aid (VIVOCA)-is described. The VIVOCA recognizes the disordered speech of the user and builds messages, which are converted into synthetic speech. System development was carried out employing user-centered design and development methods, which identified and refined key requirements for the device. A novel methodology for building small vocabulary, speaker-dependent automatic speech recognizers with reduced amounts of training data, was applied. Experiments showed that this method is successful in generating good recognition performance (mean accuracy 96%) on highly disordered speech, even when recognition perplexity is increased. The selected message-building technique traded off various factors including speed of message construction and range of available message outputs. The VIVOCA was evaluated in a field trial by individuals with moderate to severe dysarthria and confirmed that they can make use of the device to produce intelligible speech output from disordered speech input. The trial highlighted some issues which limit the performance and usability of the device when applied in real usage situations, with mean recognition accuracy of 67% in these circumstances. These limitations will be addressed in future work.

Relating dynamic brain states to dynamic machine states: Human and machine solutions to the speech recognition problem

PubMed Central

Liu, Xunying; Zhang, Chao; Woodland, Phil; Fonteneau, Elisabeth

2017-01-01

There is widespread interest in the relationship between the neurobiological systems supporting human cognition and emerging computational systems capable of emulating these capacities. Human speech comprehension, poorly understood as a neurobiological process, is an important case in point. Automatic Speech Recognition (ASR) systems with near-human levels of performance are now available, which provide a computationally explicit solution for the recognition of words in continuous speech. This research aims to bridge the gap between speech recognition processes in humans and machines, using novel multivariate techniques to compare incremental ‘machine states’, generated as the ASR analysis progresses over time, to the incremental ‘brain states’, measured using combined electro- and magneto-encephalography (EMEG), generated as the same inputs are heard by human listeners. This direct comparison of dynamic human and machine internal states, as they respond to the same incrementally delivered sensory input, revealed a significant correspondence between neural response patterns in human superior temporal cortex and the structural properties of ASR-derived phonetic models. Spatially coherent patches in human temporal cortex responded selectively to individual phonetic features defined on the basis of machine-extracted regularities in the speech to lexicon mapping process. These results demonstrate the feasibility of relating human and ASR solutions to the problem of speech recognition, and suggest the potential for further studies relating complex neural computations in human speech comprehension to the rapidly evolving ASR systems that address the same problem domain. PMID:28945744

LANDMARK-BASED SPEECH RECOGNITION: REPORT OF THE 2004 JOHNS HOPKINS SUMMER WORKSHOP.

PubMed

Hasegawa-Johnson, Mark; Baker, James; Borys, Sarah; Chen, Ken; Coogan, Emily; Greenberg, Steven; Juneja, Amit; Kirchhoff, Katrin; Livescu, Karen; Mohan, Srividya; Muller, Jennifer; Sonmez, Kemal; Wang, Tianyu

2005-01-01

Three research prototype speech recognition systems are described, all of which use recently developed methods from artificial intelligence (specifically support vector machines, dynamic Bayesian networks, and maximum entropy classification) in order to implement, in the form of an automatic speech recognizer, current theories of human speech perception and phonology (specifically landmark-based speech perception, nonlinear phonology, and articulatory phonology). All three systems begin with a high-dimensional multiframe acoustic-to-distinctive feature transformation, implemented using support vector machines trained to detect and classify acoustic phonetic landmarks. Distinctive feature probabilities estimated by the support vector machines are then integrated using one of three pronunciation models: a dynamic programming algorithm that assumes canonical pronunciation of each word, a dynamic Bayesian network implementation of articulatory phonology, or a discriminative pronunciation model trained using the methods of maximum entropy classification. Log probability scores computed by these models are then combined, using log-linear combination, with other word scores available in the lattice output of a first-pass recognizer, and the resulting combination score is used to compute a second-pass speech recognition output.

Yaounde French Speech Corpus

DTIC Science & Technology

2017-03-01

the Center for Technology Enhanced Language Learning (CTELL), a research cell in the Department of Foreign Languages, United States Military Academy...models for automatic speech recognition (ASR), and to, thereby, investigate the utility of ASR in pedagogical technology . The corpus is a sample of...lexical resources, language technology 16. SECURITY CLASSIFICATION OF: 17. LIMITATION OF ABSTRACT UU 18. NUMBER OF

Learning L2 Pronunciation with a Mobile Speech Recognizer: French /y/

ERIC Educational Resources Information Center

Liakin, Denis; Cardoso, Walcir; Liakina, Natallia

2015-01-01

This study investigates the acquisition of the L2 French vowel /y/ in a mobile-assisted learning environment, via the use of automatic speech recognition (ASR). Particularly, it addresses the question of whether ASR-based pronunciation instruction using a mobile device can improve the production and perception of French /y/. Forty-two elementary…

Transcription and Annotation of a Japanese Accented Spoken Corpus of L2 Spanish for the Development of CAPT Applications

ERIC Educational Resources Information Center

Carranza, Mario

2016-01-01

This paper addresses the process of transcribing and annotating spontaneous non-native speech with the aim of compiling a training corpus for the development of Computer Assisted Pronunciation Training (CAPT) applications, enhanced with Automatic Speech Recognition (ASR) technology. To better adapt ASR technology to CAPT tools, the recognition…

Speech recognition features for EEG signal description in detection of neonatal seizures.

PubMed

Temko, A; Boylan, G; Marnane, W; Lightbody, G

2010-01-01

In this work, features which are usually employed in automatic speech recognition (ASR) are used for the detection of neonatal seizures in newborn EEG. Three conventional ASR feature sets are compared to the feature set which has been previously developed for this task. The results indicate that the thoroughly-studied spectral envelope based ASR features perform reasonably well on their own. Additionally, the SVM Recursive Feature Elimination routine is applied to all extracted features pooled together. It is shown that ASR features consistently appear among the top-rank features.

Histogram equalization with Bayesian estimation for noise robust speech recognition.

PubMed

Suh, Youngjoo; Kim, Hoirin

2018-02-01

The histogram equalization approach is an efficient feature normalization technique for noise robust automatic speech recognition. However, it suffers from performance degradation when some fundamental conditions are not satisfied in the test environment. To remedy these limitations of the original histogram equalization methods, class-based histogram equalization approach has been proposed. Although this approach showed substantial performance improvement under noise environments, it still suffers from performance degradation due to the overfitting problem when test data are insufficient. To address this issue, the proposed histogram equalization technique employs the Bayesian estimation method in the test cumulative distribution function estimation. It was reported in a previous study conducted on the Aurora-4 task that the proposed approach provided substantial performance gains in speech recognition systems based on the acoustic modeling of the Gaussian mixture model-hidden Markov model. In this work, the proposed approach was examined in speech recognition systems with deep neural network-hidden Markov model (DNN-HMM), the current mainstream speech recognition approach where it also showed meaningful performance improvement over the conventional maximum likelihood estimation-based method. The fusion of the proposed features with the mel-frequency cepstral coefficients provided additional performance gains in DNN-HMM systems, which otherwise suffer from performance degradation in the clean test condition.

Noise-robust speech recognition through auditory feature detection and spike sequence decoding.

PubMed

Schafer, Phillip B; Jin, Dezhe Z

2014-03-01

Speech recognition in noisy conditions is a major challenge for computer systems, but the human brain performs it routinely and accurately. Automatic speech recognition (ASR) systems that are inspired by neuroscience can potentially bridge the performance gap between humans and machines. We present a system for noise-robust isolated word recognition that works by decoding sequences of spikes from a population of simulated auditory feature-detecting neurons. Each neuron is trained to respond selectively to a brief spectrotemporal pattern, or feature, drawn from the simulated auditory nerve response to speech. The neural population conveys the time-dependent structure of a sound by its sequence of spikes. We compare two methods for decoding the spike sequences--one using a hidden Markov model-based recognizer, the other using a novel template-based recognition scheme. In the latter case, words are recognized by comparing their spike sequences to template sequences obtained from clean training data, using a similarity measure based on the length of the longest common sub-sequence. Using isolated spoken digits from the AURORA-2 database, we show that our combined system outperforms a state-of-the-art robust speech recognizer at low signal-to-noise ratios. Both the spike-based encoding scheme and the template-based decoding offer gains in noise robustness over traditional speech recognition methods. Our system highlights potential advantages of spike-based acoustic coding and provides a biologically motivated framework for robust ASR development.

Dynamic relation between working memory capacity and speech recognition in noise during the first 6 months of hearing aid use.

PubMed

Ng, Elaine H N; Classon, Elisabet; Larsby, Birgitta; Arlinger, Stig; Lunner, Thomas; Rudner, Mary; Rönnberg, Jerker

2014-11-23

The present study aimed to investigate the changing relationship between aided speech recognition and cognitive function during the first 6 months of hearing aid use. Twenty-seven first-time hearing aid users with symmetrical mild to moderate sensorineural hearing loss were recruited. Aided speech recognition thresholds in noise were obtained in the hearing aid fitting session as well as at 3 and 6 months postfitting. Cognitive abilities were assessed using a reading span test, which is a measure of working memory capacity, and a cognitive test battery. Results showed a significant correlation between reading span and speech reception threshold during the hearing aid fitting session. This relation was significantly weakened over the first 6 months of hearing aid use. Multiple regression analysis showed that reading span was the main predictor of speech recognition thresholds in noise when hearing aids were first fitted, but that the pure-tone average hearing threshold was the main predictor 6 months later. One way of explaining the results is that working memory capacity plays a more important role in speech recognition in noise initially rather than after 6 months of use. We propose that new hearing aid users engage working memory capacity to recognize unfamiliar processed speech signals because the phonological form of these signals cannot be automatically matched to phonological representations in long-term memory. As familiarization proceeds, the mismatch effect is alleviated, and the engagement of working memory capacity is reduced. © The Author(s) 2014.

Factors that influence the performance of experienced speech recognition users.

PubMed

Koester, Heidi Horstmann

2006-01-01

Performance on automatic speech recognition (ASR) systems for users with physical disabilities varies widely between individuals. The goal of this study was to discover some key factors that account for that variation. Using data from 23 experienced ASR users with physical disabilities, the effect of 20 different independent variables on recognition accuracy and text entry rate with ASR was measured using bivariate and multivariate analyses. The results show that use of appropriate correction strategies had the strongest influence on user performance with ASR. The amount of time the user spent on his or her computer, the user's manual typing speed, and the speed with which the ASR system recognized speech were all positively associated with better performance. The amount or perceived adequacy of ASR training did not have a significant impact on performance for this user group.

Digital signal processing algorithms for automatic voice recognition

NASA Technical Reports Server (NTRS)

Botros, Nazeih M.

1987-01-01

The current digital signal analysis algorithms are investigated that are implemented in automatic voice recognition algorithms. Automatic voice recognition means, the capability of a computer to recognize and interact with verbal commands. The digital signal is focused on, rather than the linguistic, analysis of speech signal. Several digital signal processing algorithms are available for voice recognition. Some of these algorithms are: Linear Predictive Coding (LPC), Short-time Fourier Analysis, and Cepstrum Analysis. Among these algorithms, the LPC is the most widely used. This algorithm has short execution time and do not require large memory storage. However, it has several limitations due to the assumptions used to develop it. The other 2 algorithms are frequency domain algorithms with not many assumptions, but they are not widely implemented or investigated. However, with the recent advances in the digital technology, namely signal processors, these 2 frequency domain algorithms may be investigated in order to implement them in voice recognition. This research is concerned with real time, microprocessor based recognition algorithms.

Speech to Text: Today and Tomorrow. Proceedings of a Conference at Gallaudet University (Washington, D.C., September, 1988). GRI Monograh Series B, No. 2.

ERIC Educational Resources Information Center

Harkins, Judith E., Ed.; Virvan, Barbara M., Ed.

The conference proceedings contains 23 papers on telephone relay service, real-time captioning, and automatic speech recognition, and a glossary. The keynote address, by Representative Major R. Owens, examines current issues in federal legislation. Other papers have the following titles and authors: "Telephone Relay Service: Rationale and…

Acoustic landmarks contain more information about the phone string than other frames for automatic speech recognition with deep neural network acoustic model

NASA Astrophysics Data System (ADS)

He, Di; Lim, Boon Pang; Yang, Xuesong; Hasegawa-Johnson, Mark; Chen, Deming

2018-06-01

Most mainstream Automatic Speech Recognition (ASR) systems consider all feature frames equally important. However, acoustic landmark theory is based on a contradictory idea, that some frames are more important than others. Acoustic landmark theory exploits quantal non-linearities in the articulatory-acoustic and acoustic-perceptual relations to define landmark times at which the speech spectrum abruptly changes or reaches an extremum; frames overlapping landmarks have been demonstrated to be sufficient for speech perception. In this work, we conduct experiments on the TIMIT corpus, with both GMM and DNN based ASR systems and find that frames containing landmarks are more informative for ASR than others. We find that altering the level of emphasis on landmarks by re-weighting acoustic likelihood tends to reduce the phone error rate (PER). Furthermore, by leveraging the landmark as a heuristic, one of our hybrid DNN frame dropping strategies maintained a PER within 0.44% of optimal when scoring less than half (45.8% to be precise) of the frames. This hybrid strategy out-performs other non-heuristic-based methods and demonstrate the potential of landmarks for reducing computation.

Sentence Recognition Prediction for Hearing-impaired Listeners in Stationary and Fluctuation Noise With FADE

PubMed Central

Schädler, Marc René; Warzybok, Anna; Meyer, Bernd T.; Brand, Thomas

2016-01-01

To characterize the individual patient’s hearing impairment as obtained with the matrix sentence recognition test, a simulation Framework for Auditory Discrimination Experiments (FADE) is extended here using the Attenuation and Distortion (A+D) approach by Plomp as a blueprint for setting the individual processing parameters. FADE has been shown to predict the outcome of both speech recognition tests and psychoacoustic experiments based on simulations using an automatic speech recognition system requiring only few assumptions. It builds on the closed-set matrix sentence recognition test which is advantageous for testing individual speech recognition in a way comparable across languages. Individual predictions of speech recognition thresholds in stationary and in fluctuating noise were derived using the audiogram and an estimate of the internal level uncertainty for modeling the individual Plomp curves fitted to the data with the Attenuation (A-) and Distortion (D-) parameters of the Plomp approach. The “typical” audiogram shapes from Bisgaard et al with or without a “typical” level uncertainty and the individual data were used for individual predictions. As a result, the individualization of the level uncertainty was found to be more important than the exact shape of the individual audiogram to accurately model the outcome of the German Matrix test in stationary or fluctuating noise for listeners with hearing impairment. The prediction accuracy of the individualized approach also outperforms the (modified) Speech Intelligibility Index approach which is based on the individual threshold data only. PMID:27604782

Is talking to an automated teller machine natural and fun?

PubMed

Chan, F Y; Khalid, H M

Usability and affective issues of using automatic speech recognition technology to interact with an automated teller machine (ATM) are investigated in two experiments. The first uncovered dialogue patterns of ATM users for the purpose of designing the user interface for a simulated speech ATM system. Applying the Wizard-of-Oz methodology, multiple mapping and word spotting techniques, the speech driven ATM accommodates bilingual users of Bahasa Melayu and English. The second experiment evaluates the usability of a hybrid speech ATM, comparing it with a simulated manual ATM. The aim is to investigate how natural and fun can talking to a speech ATM be for these first-time users. Subjects performed the withdrawal and balance enquiry tasks. The ANOVA was performed on the usability and affective data. The results showed significant differences between systems in the ability to complete the tasks as well as in transaction errors. Performance was measured on the time taken by subjects to complete the task and the number of speech recognition errors that occurred. On the basis of user emotions, it can be said that the hybrid speech system enabled pleasurable interaction. Despite the limitations of speech recognition technology, users are set to talk to the ATM when it becomes available for public use.

Tone classification of syllable-segmented Thai speech based on multilayer perception

NASA Astrophysics Data System (ADS)

Satravaha, Nuttavudh; Klinkhachorn, Powsiri; Lass, Norman

2002-05-01

Thai is a monosyllabic tonal language that uses tone to convey lexical information about the meaning of a syllable. Thus to completely recognize a spoken Thai syllable, a speech recognition system not only has to recognize a base syllable but also must correctly identify a tone. Hence, tone classification of Thai speech is an essential part of a Thai speech recognition system. Thai has five distinctive tones (``mid,'' ``low,'' ``falling,'' ``high,'' and ``rising'') and each tone is represented by a single fundamental frequency (F0) pattern. However, several factors, including tonal coarticulation, stress, intonation, and speaker variability, affect the F0 pattern of a syllable in continuous Thai speech. In this study, an efficient method for tone classification of syllable-segmented Thai speech, which incorporates the effects of tonal coarticulation, stress, and intonation, as well as a method to perform automatic syllable segmentation, were developed. Acoustic parameters were used as the main discriminating parameters. The F0 contour of a segmented syllable was normalized by using a z-score transformation before being presented to a tone classifier. The proposed system was evaluated on 920 test utterances spoken by 8 speakers. A recognition rate of 91.36% was achieved by the proposed system.

Preliminary Analysis of Automatic Speech Recognition and Synthesis Technology.

DTIC Science & Technology

1983-05-01

16.311 % a. Seale In/Se"l tAL4 lrs e y i s 2 I ROM men "Ig eddiei, m releerla ons leveltc. Ŗ dots ghoeea INDtISTRtAIJ%6LITARY SPEECH SYNTHESIS PRODUCTS...saquence The SC-01 Suech Syntheszer conftains 64 cf, arent poneme~hs which are accessed try A 6-tht code. 1 - the proper sequ.enti omthnatiors of thoe...connected speech input with widely differing emotional states, diverse accents, and substantial nonperiodic background noise input. As noted previously

Effective Prediction of Errors by Non-native Speakers Using Decision Tree for Speech Recognition-Based CALL System

NASA Astrophysics Data System (ADS)

Wang, Hongcui; Kawahara, Tatsuya

CALL (Computer Assisted Language Learning) systems using ASR (Automatic Speech Recognition) for second language learning have received increasing interest recently. However, it still remains a challenge to achieve high speech recognition performance, including accurate detection of erroneous utterances by non-native speakers. Conventionally, possible error patterns, based on linguistic knowledge, are added to the lexicon and language model, or the ASR grammar network. However, this approach easily falls in the trade-off of coverage of errors and the increase of perplexity. To solve the problem, we propose a method based on a decision tree to learn effective prediction of errors made by non-native speakers. An experimental evaluation with a number of foreign students learning Japanese shows that the proposed method can effectively generate an ASR grammar network, given a target sentence, to achieve both better coverage of errors and smaller perplexity, resulting in significant improvement in ASR accuracy.

An automatic speech recognition system with speaker-independent identification support

NASA Astrophysics Data System (ADS)

Caranica, Alexandru; Burileanu, Corneliu

2015-02-01

The novelty of this work relies on the application of an open source research software toolkit (CMU Sphinx) to train, build and evaluate a speech recognition system, with speaker-independent support, for voice-controlled hardware applications. Moreover, we propose to use the trained acoustic model to successfully decode offline voice commands on embedded hardware, such as an ARMv6 low-cost SoC, Raspberry PI. This type of single-board computer, mainly used for educational and research activities, can serve as a proof-of-concept software and hardware stack for low cost voice automation systems.

Factors influencing relative speech intelligibility in patients with oral squamous cell carcinoma: a prospective study using automatic, computer-based speech analysis.

PubMed

Stelzle, F; Knipfer, C; Schuster, M; Bocklet, T; Nöth, E; Adler, W; Schempf, L; Vieler, P; Riemann, M; Neukam, F W; Nkenke, E

2013-11-01

Oral squamous cell carcinoma (OSCC) and its treatment impair speech intelligibility by alteration of the vocal tract. The aim of this study was to identify the factors of oral cancer treatment that influence speech intelligibility by means of an automatic, standardized speech-recognition system. The study group comprised 71 patients (mean age 59.89, range 35-82 years) with OSCC ranging from stage T1 to T4 (TNM staging). Tumours were located on the tongue (n=23), lower alveolar crest (n=27), and floor of the mouth (n=21). Reconstruction was conducted through local tissue plasty or microvascular transplants. Adjuvant radiotherapy was performed in 49 patients. Speech intelligibility was evaluated before, and at 3, 6, and 12 months after tumour resection, and compared to that of a healthy control group (n=40). Postoperatively, significant influences on speech intelligibility were tumour localization (P=0.010) and resection volume (P=0.019). Additionally, adjuvant radiotherapy (P=0.049) influenced intelligibility at 3 months after surgery. At 6 months after surgery, influences were resection volume (P=0.028) and adjuvant radiotherapy (P=0.034). The influence of tumour localization (P=0.001) and adjuvant radiotherapy (P=0.022) persisted after 12 months. Tumour localization, resection volume, and radiotherapy are crucial factors for speech intelligibility. Radiotherapy significantly impaired word recognition rate (WR) values with a progression of the impairment for up to 12 months after surgery. Copyright © 2013 International Association of Oral and Maxillofacial Surgeons. Published by Elsevier Ltd. All rights reserved.

The software for automatic creation of the formal grammars used by speech recognition, computer vision, editable text conversion systems, and some new functions

NASA Astrophysics Data System (ADS)

Kardava, Irakli; Tadyszak, Krzysztof; Gulua, Nana; Jurga, Stefan

2017-02-01

For more flexibility of environmental perception by artificial intelligence it is needed to exist the supporting software modules, which will be able to automate the creation of specific language syntax and to make a further analysis for relevant decisions based on semantic functions. According of our proposed approach, of which implementation it is possible to create the couples of formal rules of given sentences (in case of natural languages) or statements (in case of special languages) by helping of computer vision, speech recognition or editable text conversion system for further automatic improvement. In other words, we have developed an approach, by which it can be achieved to significantly improve the training process automation of artificial intelligence, which as a result will give us a higher level of self-developing skills independently from us (from users). At the base of our approach we have developed a software demo version, which includes the algorithm and software code for the entire above mentioned component's implementation (computer vision, speech recognition and editable text conversion system). The program has the ability to work in a multi - stream mode and simultaneously create a syntax based on receiving information from several sources.

Intonation and dialog context as constraints for speech recognition.

PubMed

Taylor, P; King, S; Isard, S; Wright, H

1998-01-01

This paper describes a way of using intonation and dialog context to improve the performance of an automatic speech recognition (ASR) system. Our experiments were run on the DCIEM Maptask corpus, a corpus of spontaneous task-oriented dialog speech. This corpus has been tagged according to a dialog analysis scheme that assigns each utterance to one of 12 "move types," such as "acknowledge," "query-yes/no" or "instruct." Most ASR systems use a bigram language model to constrain the possible sequences of words that might be recognized. Here we use a separate bigram language model for each move type. We show that when the "correct" move-specific language model is used for each utterance in the test set, the word error rate of the recognizer drops. Of course when the recognizer is run on previously unseen data, it cannot know in advance what move type the speaker has just produced. To determine the move type we use an intonation model combined with a dialog model that puts constraints on possible sequences of move types, as well as the speech recognizer likelihoods for the different move-specific models. In the full recognition system, the combination of automatic move type recognition with the move specific language models reduces the overall word error rate by a small but significant amount when compared with a baseline system that does not take intonation or dialog acts into account. Interestingly, the word error improvement is restricted to "initiating" move types, where word recognition is important. In "response" move types, where the important information is conveyed by the move type itself--for example, positive versus negative response--there is no word error improvement, but recognition of the response types themselves is good. The paper discusses the intonation model, the language models, and the dialog model in detail and describes the architecture in which they are combined.

Some effects of stress on users of a voice recognition system: A preliminary inquiry

NASA Astrophysics Data System (ADS)

French, B. A.

1983-03-01

Recent work with Automatic Speech Recognition has focused on applications and productivity considerations in the man-machine interface. This thesis is an attempt to see if placing users of such equipment under time-induced stress has an effect on their percent correct recognition rates. Subjects were given a message-handling task of fixed length and allowed progressively shorter times to attempt to complete it. Questionnaire responses indicate stress levels increased with decreased time-allowance; recognition rates decreased as time was reduced.

Sentence Recognition Prediction for Hearing-impaired Listeners in Stationary and Fluctuation Noise With FADE: Empowering the Attenuation and Distortion Concept by Plomp With a Quantitative Processing Model.

PubMed

Kollmeier, Birger; Schädler, Marc René; Warzybok, Anna; Meyer, Bernd T; Brand, Thomas

2016-09-07

To characterize the individual patient's hearing impairment as obtained with the matrix sentence recognition test, a simulation Framework for Auditory Discrimination Experiments (FADE) is extended here using the Attenuation and Distortion (A+D) approach by Plomp as a blueprint for setting the individual processing parameters. FADE has been shown to predict the outcome of both speech recognition tests and psychoacoustic experiments based on simulations using an automatic speech recognition system requiring only few assumptions. It builds on the closed-set matrix sentence recognition test which is advantageous for testing individual speech recognition in a way comparable across languages. Individual predictions of speech recognition thresholds in stationary and in fluctuating noise were derived using the audiogram and an estimate of the internal level uncertainty for modeling the individual Plomp curves fitted to the data with the Attenuation (A-) and Distortion (D-) parameters of the Plomp approach. The "typical" audiogram shapes from Bisgaard et al with or without a "typical" level uncertainty and the individual data were used for individual predictions. As a result, the individualization of the level uncertainty was found to be more important than the exact shape of the individual audiogram to accurately model the outcome of the German Matrix test in stationary or fluctuating noise for listeners with hearing impairment. The prediction accuracy of the individualized approach also outperforms the (modified) Speech Intelligibility Index approach which is based on the individual threshold data only. © The Author(s) 2016.

Estimating psycho-physiological state of a human by speech analysis

NASA Astrophysics Data System (ADS)

Ronzhin, A. L.

2005-05-01

Adverse effects of intoxication, fatigue and boredom could degrade performance of highly trained operators of complex technical systems with potentially catastrophic consequences. Existing physiological fitness for duty tests are time consuming, costly, invasive, and highly unpopular. Known non-physiological tests constitute a secondary task and interfere with the busy workload of the tested operator. Various attempts to assess the current status of the operator by processing of "normal operational data" often lead to excessive amount of computations, poorly justified metrics, and ambiguity of results. At the same time, speech analysis presents a natural, non-invasive approach based upon well-established efficient data processing. In addition, it supports both behavioral and physiological biometric. This paper presents an approach facilitating robust speech analysis/understanding process in spite of natural speech variability and background noise. Automatic speech recognition is suggested as a technique for the detection of changes in the psycho-physiological state of a human that typically manifest themselves by changes of characteristics of voice tract and semantic-syntactic connectivity of conversation. Preliminary tests have confirmed that the statistically significant correlation between the error rate of automatic speech recognition and the extent of alcohol intoxication does exist. In addition, the obtained data allowed exploring some interesting correlations and establishing some quantitative models. It is proposed to utilize this approach as a part of fitness for duty test and compare its efficiency with analyses of iris, face geometry, thermography and other popular non-invasive biometric techniques.

Sound Classification in Hearing Aids Inspired by Auditory Scene Analysis

NASA Astrophysics Data System (ADS)

Büchler, Michael; Allegro, Silvia; Launer, Stefan; Dillier, Norbert

2005-12-01

A sound classification system for the automatic recognition of the acoustic environment in a hearing aid is discussed. The system distinguishes the four sound classes "clean speech," "speech in noise," "noise," and "music." A number of features that are inspired by auditory scene analysis are extracted from the sound signal. These features describe amplitude modulations, spectral profile, harmonicity, amplitude onsets, and rhythm. They are evaluated together with different pattern classifiers. Simple classifiers, such as rule-based and minimum-distance classifiers, are compared with more complex approaches, such as Bayes classifier, neural network, and hidden Markov model. Sounds from a large database are employed for both training and testing of the system. The achieved recognition rates are very high except for the class "speech in noise." Problems arise in the classification of compressed pop music, strongly reverberated speech, and tonal or fluctuating noises.

A Cross-Lingual Mobile Medical Communication System Prototype for Foreigners and Subjects with Speech, Hearing, and Mental Disabilities Based on Pictograms

PubMed Central

Wołk, Agnieszka; Glinkowski, Wojciech

2017-01-01

People with speech, hearing, or mental impairment require special communication assistance, especially for medical purposes. Automatic solutions for speech recognition and voice synthesis from text are poor fits for communication in the medical domain because they are dependent on error-prone statistical models. Systems dependent on manual text input are insufficient. Recently introduced systems for automatic sign language recognition are dependent on statistical models as well as on image and gesture quality. Such systems remain in early development and are based mostly on minimal hand gestures unsuitable for medical purposes. Furthermore, solutions that rely on the Internet cannot be used after disasters that require humanitarian aid. We propose a high-speed, intuitive, Internet-free, voice-free, and text-free tool suited for emergency medical communication. Our solution is a pictogram-based application that provides easy communication for individuals who have speech or hearing impairment or mental health issues that impair communication, as well as foreigners who do not speak the local language. It provides support and clarification in communication by using intuitive icons and interactive symbols that are easy to use on a mobile device. Such pictogram-based communication can be quite effective and ultimately make people's lives happier, easier, and safer. PMID:29230254

A Cross-Lingual Mobile Medical Communication System Prototype for Foreigners and Subjects with Speech, Hearing, and Mental Disabilities Based on Pictograms.

PubMed

Wołk, Krzysztof; Wołk, Agnieszka; Glinkowski, Wojciech

2017-01-01

People with speech, hearing, or mental impairment require special communication assistance, especially for medical purposes. Automatic solutions for speech recognition and voice synthesis from text are poor fits for communication in the medical domain because they are dependent on error-prone statistical models. Systems dependent on manual text input are insufficient. Recently introduced systems for automatic sign language recognition are dependent on statistical models as well as on image and gesture quality. Such systems remain in early development and are based mostly on minimal hand gestures unsuitable for medical purposes. Furthermore, solutions that rely on the Internet cannot be used after disasters that require humanitarian aid. We propose a high-speed, intuitive, Internet-free, voice-free, and text-free tool suited for emergency medical communication. Our solution is a pictogram-based application that provides easy communication for individuals who have speech or hearing impairment or mental health issues that impair communication, as well as foreigners who do not speak the local language. It provides support and clarification in communication by using intuitive icons and interactive symbols that are easy to use on a mobile device. Such pictogram-based communication can be quite effective and ultimately make people's lives happier, easier, and safer.

Computational validation of the motor contribution to speech perception.

PubMed

Badino, Leonardo; D'Ausilio, Alessandro; Fadiga, Luciano; Metta, Giorgio

2014-07-01

Action perception and recognition are core abilities fundamental for human social interaction. A parieto-frontal network (the mirror neuron system) matches visually presented biological motion information onto observers' motor representations. This process of matching the actions of others onto our own sensorimotor repertoire is thought to be important for action recognition, providing a non-mediated "motor perception" based on a bidirectional flow of information along the mirror parieto-frontal circuits. State-of-the-art machine learning strategies for hand action identification have shown better performances when sensorimotor data, as opposed to visual information only, are available during learning. As speech is a particular type of action (with acoustic targets), it is expected to activate a mirror neuron mechanism. Indeed, in speech perception, motor centers have been shown to be causally involved in the discrimination of speech sounds. In this paper, we review recent neurophysiological and machine learning-based studies showing (a) the specific contribution of the motor system to speech perception and (b) that automatic phone recognition is significantly improved when motor data are used during training of classifiers (as opposed to learning from purely auditory data). Copyright © 2014 Cognitive Science Society, Inc.

Automatic measurement and representation of prosodic features

NASA Astrophysics Data System (ADS)

Ying, Goangshiuan Shawn

Effective measurement and representation of prosodic features of the acoustic signal for use in automatic speech recognition and understanding systems is the goal of this work. Prosodic features-stress, duration, and intonation-are variations of the acoustic signal whose domains are beyond the boundaries of each individual phonetic segment. Listeners perceive prosodic features through a complex combination of acoustic correlates such as intensity, duration, and fundamental frequency (F0). We have developed new tools to measure F0 and intensity features. We apply a probabilistic global error correction routine to an Average Magnitude Difference Function (AMDF) pitch detector. A new short-term frequency-domain Teager energy algorithm is used to measure the energy of a speech signal. We have conducted a series of experiments performing lexical stress detection on words in continuous English speech from two speech corpora. We have experimented with two different approaches, a segment-based approach and a rhythm unit-based approach, in lexical stress detection. The first approach uses pattern recognition with energy- and duration-based measurements as features to build Bayesian classifiers to detect the stress level of a vowel segment. In the second approach we define rhythm unit and use only the F0-based measurement and a scoring system to determine the stressed segment in the rhythm unit. A duration-based segmentation routine was developed to break polysyllabic words into rhythm units. The long-term goal of this work is to develop a system that can effectively detect the stress pattern for each word in continuous speech utterances. Stress information will be integrated as a constraint for pruning the word hypotheses in a word recognition system based on hidden Markov models.

Analysis of human scream and its impact on text-independent speaker verification.

PubMed

Hansen, John H L; Nandwana, Mahesh Kumar; Shokouhi, Navid

2017-04-01

Scream is defined as sustained, high-energy vocalizations that lack phonological structure. Lack of phonological structure is how scream is identified from other forms of loud vocalization, such as "yell." This study investigates the acoustic aspects of screams and addresses those that are known to prevent standard speaker identification systems from recognizing the identity of screaming speakers. It is well established that speaker variability due to changes in vocal effort and Lombard effect contribute to degraded performance in automatic speech systems (i.e., speech recognition, speaker identification, diarization, etc.). However, previous research in the general area of speaker variability has concentrated on human speech production, whereas less is known about non-speech vocalizations. The UT-NonSpeech corpus is developed here to investigate speaker verification from scream samples. This study considers a detailed analysis in terms of fundamental frequency, spectral peak shift, frame energy distribution, and spectral tilt. It is shown that traditional speaker recognition based on the Gaussian mixture models-universal background model framework is unreliable when evaluated with screams.

A multi-views multi-learners approach towards dysarthric speech recognition using multi-nets artificial neural networks.

PubMed

Shahamiri, Seyed Reza; Salim, Siti Salwah Binti

2014-09-01

Automatic speech recognition (ASR) can be very helpful for speakers who suffer from dysarthria, a neurological disability that damages the control of motor speech articulators. Although a few attempts have been made to apply ASR technologies to sufferers of dysarthria, previous studies show that such ASR systems have not attained an adequate level of performance. In this study, a dysarthric multi-networks speech recognizer (DM-NSR) model is provided using a realization of multi-views multi-learners approach called multi-nets artificial neural networks, which tolerates variability of dysarthric speech. In particular, the DM-NSR model employs several ANNs (as learners) to approximate the likelihood of ASR vocabulary words and to deal with the complexity of dysarthric speech. The proposed DM-NSR approach was presented as both speaker-dependent and speaker-independent paradigms. In order to highlight the performance of the proposed model over legacy models, multi-views single-learner models of the DM-NSRs were also provided and their efficiencies were compared in detail. Moreover, a comparison among the prominent dysarthric ASR methods and the proposed one is provided. The results show that the DM-NSR recorded improved recognition rate by up to 24.67% and the error rate was reduced by up to 8.63% over the reference model.

Foreign Language Analysis and Recognition (FLARE) Progress

DTIC Science & Technology

2015-02-01

Copies may be obtained from the Defense Technical Information Center (DTIC) (http://www.dtic.mil). AFRL- RH -WP-TR-2015-0007 HAS BEEN REVIEWED AND IS... retrieval (IR). 15. SUBJECT TERMS Automatic speech recognition (ASR), information retrieval (IR). 16. SECURITY CLASSIFICATION OF: 17. LIMITATION OF...to the Haystack Multilingual Multimedia Information Extraction and Retrieval (MMIER) system that was initially developed under a prior work unit

Early Detection of Severe Apnoea through Voice Analysis and Automatic Speaker Recognition Techniques

NASA Astrophysics Data System (ADS)

Fernández, Ruben; Blanco, Jose Luis; Díaz, David; Hernández, Luis A.; López, Eduardo; Alcázar, José

This study is part of an on-going collaborative effort between the medical and the signal processing communities to promote research on applying voice analysis and Automatic Speaker Recognition techniques (ASR) for the automatic diagnosis of patients with severe obstructive sleep apnoea (OSA). Early detection of severe apnoea cases is important so that patients can receive early treatment. Effective ASR-based diagnosis could dramatically cut medical testing time. Working with a carefully designed speech database of healthy and apnoea subjects, we present and discuss the possibilities of using generative Gaussian Mixture Models (GMMs), generally used in ASR systems, to model distinctive apnoea voice characteristics (i.e. abnormal nasalization). Finally, we present experimental findings regarding the discriminative power of speaker recognition techniques applied to severe apnoea detection. We have achieved an 81.25 % correct classification rate, which is very promising and underpins the interest in this line of inquiry.

Restoring the missing features of the corrupted speech using linear interpolation methods

NASA Astrophysics Data System (ADS)

Rassem, Taha H.; Makbol, Nasrin M.; Hasan, Ali Muttaleb; Zaki, Siti Syazni Mohd; Girija, P. N.

2017-10-01

One of the main challenges in the Automatic Speech Recognition (ASR) is the noise. The performance of the ASR system reduces significantly if the speech is corrupted by noise. In spectrogram representation of a speech signal, after deleting low Signal to Noise Ratio (SNR) elements, the incomplete spectrogram is obtained. In this case, the speech recognizer should make modifications to the spectrogram in order to restore the missing elements, which is one direction. In another direction, speech recognizer should be able to restore the missing elements due to deleting low SNR elements before performing the recognition. This is can be done using different spectrogram reconstruction methods. In this paper, the geometrical spectrogram reconstruction methods suggested by some researchers are implemented as a toolbox. In these geometrical reconstruction methods, the linear interpolation along time or frequency methods are used to predict the missing elements between adjacent observed elements in the spectrogram. Moreover, a new linear interpolation method using time and frequency together is presented. The CMU Sphinx III software is used in the experiments to test the performance of the linear interpolation reconstruction method. The experiments are done under different conditions such as different lengths of the window and different lengths of utterances. Speech corpus consists of 20 males and 20 females; each one has two different utterances are used in the experiments. As a result, 80% recognition accuracy is achieved with 25% SNR ratio.

Modular Neural Networks for Speech Recognition.

DTIC Science & Technology

1996-08-01

automatic speech rccogni- tion, understanding and translation since the early 1950’ s . Although researchers have demonstrated impressive results with...nodes. It serves only as a data source for the following hidden layer( s ). Finally, the networks output is computed by neurons in the output layer. The...following update rule for weights in the hidden layer: w (,,•+I) ("’) E/V S (W W k- = wj, -- 7 - / v It is easy to generalize the backpropagation

EMG-based speech recognition using hidden markov models with global control variables.

PubMed

Lee, Ki-Seung

2008-03-01

It is well known that a strong relationship exists between human voices and the movement of articulatory facial muscles. In this paper, we utilize this knowledge to implement an automatic speech recognition scheme which uses solely surface electromyogram (EMG) signals. The sequence of EMG signals for each word is modelled by a hidden Markov model (HMM) framework. The main objective of the work involves building a model for state observation density when multichannel observation sequences are given. The proposed model reflects the dependencies between each of the EMG signals, which are described by introducing a global control variable. We also develop an efficient model training method, based on a maximum likelihood criterion. In a preliminary study, 60 isolated words were used as recognition variables. EMG signals were acquired from three articulatory facial muscles. The findings indicate that such a system may have the capacity to recognize speech signals with an accuracy of up to 87.07%, which is superior to the independent probabilistic model.

A new time-adaptive discrete bionic wavelet transform for enhancing speech from adverse noise environment

NASA Astrophysics Data System (ADS)

Palaniswamy, Sumithra; Duraisamy, Prakash; Alam, Mohammad Showkat; Yuan, Xiaohui

2012-04-01

Automatic speech processing systems are widely used in everyday life such as mobile communication, speech and speaker recognition, and for assisting the hearing impaired. In speech communication systems, the quality and intelligibility of speech is of utmost importance for ease and accuracy of information exchange. To obtain an intelligible speech signal and one that is more pleasant to listen, noise reduction is essential. In this paper a new Time Adaptive Discrete Bionic Wavelet Thresholding (TADBWT) scheme is proposed. The proposed technique uses Daubechies mother wavelet to achieve better enhancement of speech from additive non- stationary noises which occur in real life such as street noise and factory noise. Due to the integration of human auditory system model into the wavelet transform, bionic wavelet transform (BWT) has great potential for speech enhancement which may lead to a new path in speech processing. In the proposed technique, at first, discrete BWT is applied to noisy speech to derive TADBWT coefficients. Then the adaptive nature of the BWT is captured by introducing a time varying linear factor which updates the coefficients at each scale over time. This approach has shown better performance than the existing algorithms at lower input SNR due to modified soft level dependent thresholding on time adaptive coefficients. The objective and subjective test results confirmed the competency of the TADBWT technique. The effectiveness of the proposed technique is also evaluated for speaker recognition task under noisy environment. The recognition results show that the TADWT technique yields better performance when compared to alternate methods specifically at lower input SNR.

Technological evaluation of gesture and speech interfaces for enabling dismounted soldier-robot dialogue

NASA Astrophysics Data System (ADS)

Kattoju, Ravi Kiran; Barber, Daniel J.; Abich, Julian; Harris, Jonathan

2016-05-01

With increasing necessity for intuitive Soldier-robot communication in military operations and advancements in interactive technologies, autonomous robots have transitioned from assistance tools to functional and operational teammates able to service an array of military operations. Despite improvements in gesture and speech recognition technologies, their effectiveness in supporting Soldier-robot communication is still uncertain. The purpose of the present study was to evaluate the performance of gesture and speech interface technologies to facilitate Soldier-robot communication during a spatial-navigation task with an autonomous robot. Gesture and speech semantically based spatial-navigation commands leveraged existing lexicons for visual and verbal communication from the U.S Army field manual for visual signaling and a previously established Squad Level Vocabulary (SLV). Speech commands were recorded by a Lapel microphone and Microsoft Kinect, and classified by commercial off-the-shelf automatic speech recognition (ASR) software. Visual signals were captured and classified using a custom wireless gesture glove and software. Participants in the experiment commanded a robot to complete a simulated ISR mission in a scaled down urban scenario by delivering a sequence of gesture and speech commands, both individually and simultaneously, to the robot. Performance and reliability of gesture and speech hardware interfaces and recognition tools were analyzed and reported. Analysis of experimental results demonstrated the employed gesture technology has significant potential for enabling bidirectional Soldier-robot team dialogue based on the high classification accuracy and minimal training required to perform gesture commands.

User Evaluation of a Communication System That Automatically Generates Captions to Improve Telephone Communication

PubMed Central

Zekveld, Adriana A.; Kramer, Sophia E.; Kessens, Judith M.; Vlaming, Marcel S. M. G.; Houtgast, Tammo

2009-01-01

This study examined the subjective benefit obtained from automatically generated captions during telephone-speech comprehension in the presence of babble noise. Short stories were presented by telephone either with or without captions that were generated offline by an automatic speech recognition (ASR) system. To simulate online ASR, the word accuracy (WA) level of the captions was 60% or 70% and the text was presented delayed to the speech. After each test, the hearing impaired participants (n = 20) completed the NASA-Task Load Index and several rating scales evaluating the support from the captions. Participants indicated that using the erroneous text in speech comprehension was difficult and the reported task load did not differ between the audio + text and audio-only conditions. In a follow-up experiment (n = 10), the perceived benefit of presenting captions increased with an increase of WA levels to 80% and 90%, and elimination of the text delay. However, in general, the task load did not decrease when captions were presented. These results suggest that the extra effort required to process the text could have been compensated for by less effort required to comprehend the speech. Future research should aim at reducing the complexity of the task to increase the willingness of hearing impaired persons to use an assistive communication system automatically providing captions. The current results underline the need for obtaining both objective and subjective measures of benefit when evaluating assistive communication systems. PMID:19126551

Automatic speech recognition research at NASA-Ames Research Center

NASA Technical Reports Server (NTRS)

Coler, Clayton R.; Plummer, Robert P.; Huff, Edward M.; Hitchcock, Myron H.

1977-01-01

A trainable acoustic pattern recognizer manufactured by Scope Electronics is presented. The voice command system VCS encodes speech by sampling 16 bandpass filters with center frequencies in the range from 200 to 5000 Hz. Variations in speaking rate are compensated for by a compression algorithm that subdivides each utterance into eight subintervals in such a way that the amount of spectral change within each subinterval is the same. The recorded filter values within each subinterval are then reduced to a 15-bit representation, giving a 120-bit encoding for each utterance. The VCS incorporates a simple recognition algorithm that utilizes five training samples of each word in a vocabulary of up to 24 words. The recognition rate of approximately 85 percent correct for untrained speakers and 94 percent correct for trained speakers was not considered adequate for flight systems use. Therefore, the built-in recognition algorithm was disabled, and the VCS was modified to transmit 120-bit encodings to an external computer for recognition.

Acoustic Event Detection and Classification

NASA Astrophysics Data System (ADS)

Temko, Andrey; Nadeu, Climent; Macho, Dušan; Malkin, Robert; Zieger, Christian; Omologo, Maurizio

The human activity that takes place in meeting rooms or classrooms is reflected in a rich variety of acoustic events (AE), produced either by the human body or by objects handled by humans, so the determination of both the identity of sounds and their position in time may help to detect and describe that human activity. Indeed, speech is usually the most informative sound, but other kinds of AEs may also carry useful information, for example, clapping or laughing inside a speech, a strong yawn in the middle of a lecture, a chair moving or a door slam when the meeting has just started. Additionally, detection and classification of sounds other than speech may be useful to enhance the robustness of speech technologies like automatic speech recognition.

Sound and speech detection and classification in a Health Smart Home.

PubMed

Fleury, A; Noury, N; Vacher, M; Glasson, H; Seri, J F

2008-01-01

Improvements in medicine increase life expectancy in the world and create a new bottleneck at the entrance of specialized and equipped institutions. To allow elderly people to stay at home, researchers work on ways to monitor them in their own environment, with non-invasive sensors. To meet this goal, smart homes, equipped with lots of sensors, deliver information on the activities of the person and can help detect distress situations. In this paper, we present a global speech and sound recognition system that can be set-up in a flat. We placed eight microphones in the Health Smart Home of Grenoble (a real living flat of 47m(2)) and we automatically analyze and sort out the different sounds recorded in the flat and the speech uttered (to detect normal or distress french sentences). We introduce the methods for the sound and speech recognition, the post-processing of the data and finally the experimental results obtained in real conditions in the flat.

Research Directory for Manpower, Personnel, Training, and Human Factors.

DTIC Science & Technology

1991-01-01

Enhance Automatic Recognition of Speech in Noisy, Highly Stressful Environments Cofod R* Lica Systems Inc 703-359-0996 Smart Contract Preparation...Lab 301-278-2946 Smart Contract Preparation Expediter Frezell T LTCOL Human Engineering Lab 301-278-5998 Impulse Noise Hazard Information Processing R&D

On the Development of Speech Resources for the Mixtec Language

PubMed Central

2013-01-01

The Mixtec language is one of the main native languages in Mexico. In general, due to urbanization, discrimination, and limited attempts to promote the culture, the native languages are disappearing. Most of the information available about the Mixtec language is in written form as in dictionaries which, although including examples about how to pronounce the Mixtec words, are not as reliable as listening to the correct pronunciation from a native speaker. Formal acoustic resources, as speech corpora, are almost non-existent for the Mixtec, and no speech technologies are known to have been developed for it. This paper presents the development of the following resources for the Mixtec language: (1) a speech database of traditional narratives of the Mixtec culture spoken by a native speaker (labelled at the phonetic and orthographic levels by means of spectral analysis) and (2) a native speaker-adaptive automatic speech recognition (ASR) system (trained with the speech database) integrated with a Mixtec-to-Spanish/Spanish-to-Mixtec text translator. The speech database, although small and limited to a single variant, was reliable enough to build the multiuser speech application which presented a mean recognition/translation performance up to 94.36% in experiments with non-native speakers (the target users). PMID:23710134

Statistical Evaluation of Biometric Evidence in Forensic Automatic Speaker Recognition

NASA Astrophysics Data System (ADS)

Drygajlo, Andrzej

Forensic speaker recognition is the process of determining if a specific individual (suspected speaker) is the source of a questioned voice recording (trace). This paper aims at presenting forensic automatic speaker recognition (FASR) methods that provide a coherent way of quantifying and presenting recorded voice as biometric evidence. In such methods, the biometric evidence consists of the quantified degree of similarity between speaker-dependent features extracted from the trace and speaker-dependent features extracted from recorded speech of a suspect. The interpretation of recorded voice as evidence in the forensic context presents particular challenges, including within-speaker (within-source) variability and between-speakers (between-sources) variability. Consequently, FASR methods must provide a statistical evaluation which gives the court an indication of the strength of the evidence given the estimated within-source and between-sources variabilities. This paper reports on the first ENFSI evaluation campaign through a fake case, organized by the Netherlands Forensic Institute (NFI), as an example, where an automatic method using the Gaussian mixture models (GMMs) and the Bayesian interpretation (BI) framework were implemented for the forensic speaker recognition task.

Modeling the Perceptual Learning of Novel Dialect Features

ERIC Educational Resources Information Center

Tatman, Rachael

2017-01-01

All language use reflects the user's social identity in systematic ways. While humans can easily adapt to this sociolinguistic variation, automatic speech recognition (ASR) systems continue to struggle with it. This dissertation makes three main contributions. The first is to provide evidence that modern state-of-the-art commercial ASR systems…

Morphosyntactic Neural Analysis for Generalized Lexical Normalization

ERIC Educational Resources Information Center

Leeman-Munk, Samuel Paul

2016-01-01

The phenomenal growth of social media, web forums, and online reviews has spurred a growing interest in automated analysis of user-generated text. At the same time, a proliferation of voice recordings and efforts to archive culture heritage documents are fueling demand for effective automatic speech recognition (ASR) and optical character…

Multilingual Videos for MOOCs and OER

ERIC Educational Resources Information Center

Valor Miró, Juan Daniel; Baquero-Arnal, Pau; Civera, Jorge; Turró, Carlos; Juan, Alfons

2018-01-01

Massive Open Online Courses (MOOCs) and Open Educational Resources (OER) are rapidly growing, but are not usually offered in multiple languages due to the lack of cost-effective solutions to translate the different objects comprising them and particularly videos. However, current state-of-the-art automatic speech recognition (ASR) and machine…

Text as a Supplement to Speech in Young and Older Adults a)

PubMed Central

Krull, Vidya; Humes, Larry E.

2015-01-01

Objective The purpose of this experiment was to quantify the contribution of visual text to auditory speech recognition in background noise. Specifically, we tested the hypothesis that partially accurate visual text from an automatic speech recognizer could be used successfully to supplement speech understanding in difficult listening conditions in older adults, with normal or impaired hearing. Our working hypotheses were based on what is known regarding audiovisual speech perception in the elderly from speechreading literature. We hypothesized that: 1) combining auditory and visual text information will result in improved recognition accuracy compared to auditory or visual text information alone; 2) benefit from supplementing speech with visual text (auditory and visual enhancement) in young adults will be greater than that in older adults; and 3) individual differences in performance on perceptual measures would be associated with cognitive abilities. Design Fifteen young adults with normal hearing, fifteen older adults with normal hearing, and fifteen older adults with hearing loss participated in this study. All participants completed sentence recognition tasks in auditory-only, text-only, and combined auditory-text conditions. The auditory sentence stimuli were spectrally shaped to restore audibility for the older participants with impaired hearing. All participants also completed various cognitive measures, including measures of working memory, processing speed, verbal comprehension, perceptual and cognitive speed, processing efficiency, inhibition, and the ability to form wholes from parts. Group effects were examined for each of the perceptual and cognitive measures. Audiovisual benefit was calculated relative to performance on auditory-only and visual-text only conditions. Finally, the relationship between perceptual measures and other independent measures were examined using principal-component factor analyses, followed by regression analyses. Results Both young and older adults performed similarly on nine out of ten perceptual measures (auditory, visual, and combined measures). Combining degraded speech with partially correct text from an automatic speech recognizer improved the understanding of speech in both young and older adults, relative to both auditory- and text-only performance. In all subjects, cognition emerged as a key predictor for a general speech-text integration ability. Conclusions These results suggest that neither age nor hearing loss affected the ability of subjects to benefit from text when used to support speech, after ensuring audibility through spectral shaping. These results also suggest that the benefit obtained by supplementing auditory input with partially accurate text is modulated by cognitive ability, specifically lexical and verbal skills. PMID:26458131

An attention-gating recurrent working memory architecture for emergent speech representation

NASA Astrophysics Data System (ADS)

Elshaw, Mark; Moore, Roger K.; Klein, Michael

2010-06-01

This paper describes an attention-gating recurrent self-organising map approach for emergent speech representation. Inspired by evidence from human cognitive processing, the architecture combines two main neural components. The first component, the attention-gating mechanism, uses actor-critic learning to perform selective attention towards speech. Through this selective attention approach, the attention-gating mechanism controls access to working memory processing. The second component, the recurrent self-organising map memory, develops a temporal-distributed representation of speech using phone-like structures. Representing speech in terms of phonetic features in an emergent self-organised fashion, according to research on child cognitive development, recreates the approach found in infants. Using this representational approach, in a fashion similar to infants, should improve the performance of automatic recognition systems through aiding speech segmentation and fast word learning.

Real-time speech gisting for ATC applications

NASA Astrophysics Data System (ADS)

Dunkelberger, Kirk A.

1995-06-01

Command and control within the ATC environment remains primarily voice-based. Hence, automatic real time, speaker independent, continuous speech recognition (CSR) has many obvious applications and implied benefits to the ATC community: automated target tagging, aircraft compliance monitoring, controller training, automatic alarm disabling, display management, and many others. However, while current state-of-the-art CSR systems provide upwards of 98% word accuracy in laboratory environments, recent low-intrusion experiments in the ATCT environments demonstrated less than 70% word accuracy in spite of significant investments in recognizer tuning. Acoustic channel irregularities and controller/pilot grammar verities impact current CSR algorithms at their weakest points. It will be shown herein, however, that real time context- and environment-sensitive gisting can provide key command phrase recognition rates of greater than 95% using the same low-intrusion approach. The combination of real time inexact syntactic pattern recognition techniques and a tight integration of CSR, gisting, and ATC database accessor system components is the key to these high phase recognition rates. A system concept for real time gisting in the ATC context is presented herein. After establishing an application context, discussion presents a minimal CSR technology context then focuses on the gisting mechanism, desirable interfaces into the ATCT database environment, and data and control flow within the prototype system. Results of recent tests for a subset of the functionality are presented together with suggestions for further research.

DARPA TIMIT acoustic-phonetic continous speech corpus CD-ROM. NIST speech disc 1-1.1

NASA Astrophysics Data System (ADS)

Garofolo, J. S.; Lamel, L. F.; Fisher, W. M.; Fiscus, J. G.; Pallett, D. S.

1993-02-01

The Texas Instruments/Massachusetts Institute of Technology (TIMIT) corpus of read speech has been designed to provide speech data for the acquisition of acoustic-phonetic knowledge and for the development and evaluation of automatic speech recognition systems. TIMIT contains speech from 630 speakers representing 8 major dialect divisions of American English, each speaking 10 phonetically-rich sentences. The TIMIT corpus includes time-aligned orthographic, phonetic, and word transcriptions, as well as speech waveform data for each spoken sentence. The release of TIMIT contains several improvements over the Prototype CD-ROM released in December, 1988: (1) full 630-speaker corpus, (2) checked and corrected transcriptions, (3) word-alignment transcriptions, (4) NIST SPHERE-headered waveform files and header manipulation software, (5) phonemic dictionary, (6) new test and training subsets balanced for dialectal and phonetic coverage, and (7) more extensive documentation.

Auditory-Motor Processing of Speech Sounds

PubMed Central

Möttönen, Riikka; Dutton, Rebekah; Watkins, Kate E.

2013-01-01

The motor regions that control movements of the articulators activate during listening to speech and contribute to performance in demanding speech recognition and discrimination tasks. Whether the articulatory motor cortex modulates auditory processing of speech sounds is unknown. Here, we aimed to determine whether the articulatory motor cortex affects the auditory mechanisms underlying discrimination of speech sounds in the absence of demanding speech tasks. Using electroencephalography, we recorded responses to changes in sound sequences, while participants watched a silent video. We also disrupted the lip or the hand representation in left motor cortex using transcranial magnetic stimulation. Disruption of the lip representation suppressed responses to changes in speech sounds, but not piano tones. In contrast, disruption of the hand representation had no effect on responses to changes in speech sounds. These findings show that disruptions within, but not outside, the articulatory motor cortex impair automatic auditory discrimination of speech sounds. The findings provide evidence for the importance of auditory-motor processes in efficient neural analysis of speech sounds. PMID:22581846

Alternative Speech Communication System for Persons with Severe Speech Disorders

NASA Astrophysics Data System (ADS)

Selouani, Sid-Ahmed; Sidi Yakoub, Mohammed; O'Shaughnessy, Douglas

2009-12-01

Assistive speech-enabled systems are proposed to help both French and English speaking persons with various speech disorders. The proposed assistive systems use automatic speech recognition (ASR) and speech synthesis in order to enhance the quality of communication. These systems aim at improving the intelligibility of pathologic speech making it as natural as possible and close to the original voice of the speaker. The resynthesized utterances use new basic units, a new concatenating algorithm and a grafting technique to correct the poorly pronounced phonemes. The ASR responses are uttered by the new speech synthesis system in order to convey an intelligible message to listeners. Experiments involving four American speakers with severe dysarthria and two Acadian French speakers with sound substitution disorders (SSDs) are carried out to demonstrate the efficiency of the proposed methods. An improvement of the Perceptual Evaluation of the Speech Quality (PESQ) value of 5% and more than 20% is achieved by the speech synthesis systems that deal with SSD and dysarthria, respectively.

Spoken Grammar Practice and Feedback in an ASR-Based CALL System

ERIC Educational Resources Information Center

de Vries, Bart Penning; Cucchiarini, Catia; Bodnar, Stephen; Strik, Helmer; van Hout, Roeland

2015-01-01

Speaking practice is important for learners of a second language. Computer assisted language learning (CALL) systems can provide attractive opportunities for speaking practice when combined with automatic speech recognition (ASR) technology. In this paper, we present a CALL system that offers spoken practice of word order, an important aspect of…

Effectiveness of Feedback for Enhancing English Pronunciation in an ASR-Based CALL System

ERIC Educational Resources Information Center

Wang, Y.-H.; Young, S. S.-C.

2015-01-01

This paper presents a study on implementing the ASR-based CALL (computer-assisted language learning based upon automatic speech recognition) system embedded with both formative and summative feedback approaches and using implicit and explicit strategies to enhance adult and young learners' English pronunciation. Two groups of learners including 18…

The Influence of Anticipation of Word Misrecognition on the Likelihood of Stuttering

ERIC Educational Resources Information Center

Brocklehurst, Paul H.; Lickley, Robin J.; Corley, Martin

2012-01-01

This study investigates whether the experience of stuttering can result from the speaker's anticipation of his words being misrecognized. Twelve adults who stutter (AWS) repeated single words into what appeared to be an automatic speech-recognition system. Following each iteration of each word, participants provided a self-rating of whether they…

MARTI: man-machine animation real-time interface

NASA Astrophysics Data System (ADS)

Jones, Christian M.; Dlay, Satnam S.

1997-05-01

The research introduces MARTI (man-machine animation real-time interface) for the realization of natural human-machine interfacing. The system uses simple vocal sound-tracks of human speakers to provide lip synchronization of computer graphical facial models. We present novel research in a number of engineering disciplines, which include speech recognition, facial modeling, and computer animation. This interdisciplinary research utilizes the latest, hybrid connectionist/hidden Markov model, speech recognition system to provide very accurate phone recognition and timing for speaker independent continuous speech, and expands on knowledge from the animation industry in the development of accurate facial models and automated animation. The research has many real-world applications which include the provision of a highly accurate and 'natural' man-machine interface to assist user interactions with computer systems and communication with one other using human idiosyncrasies; a complete special effects and animation toolbox providing automatic lip synchronization without the normal constraints of head-sets, joysticks, and skilled animators; compression of video data to well below standard telecommunication channel bandwidth for video communications and multi-media systems; assisting speech training and aids for the handicapped; and facilitating player interaction for 'video gaming' and 'virtual worlds.' MARTI has introduced a new level of realism to man-machine interfacing and special effect animation which has been previously unseen.

Automated Intelligibility Assessment of Pathological Speech Using Phonological Features

NASA Astrophysics Data System (ADS)

Middag, Catherine; Martens, Jean-Pierre; Van Nuffelen, Gwen; De Bodt, Marc

2009-12-01

It is commonly acknowledged that word or phoneme intelligibility is an important criterion in the assessment of the communication efficiency of a pathological speaker. People have therefore put a lot of effort in the design of perceptual intelligibility rating tests. These tests usually have the drawback that they employ unnatural speech material (e.g., nonsense words) and that they cannot fully exclude errors due to listener bias. Therefore, there is a growing interest in the application of objective automatic speech recognition technology to automate the intelligibility assessment. Current research is headed towards the design of automated methods which can be shown to produce ratings that correspond well with those emerging from a well-designed and well-performed perceptual test. In this paper, a novel methodology that is built on previous work (Middag et al., 2008) is presented. It utilizes phonological features, automatic speech alignment based on acoustic models that were trained on normal speech, context-dependent speaker feature extraction, and intelligibility prediction based on a small model that can be trained on pathological speech samples. The experimental evaluation of the new system reveals that the root mean squared error of the discrepancies between perceived and computed intelligibilities can be as low as 8 on a scale of 0 to 100.

Tuning time-frequency methods for the detection of metered HF speech

NASA Astrophysics Data System (ADS)

Nelson, Douglas J.; Smith, Lawrence H.

2002-12-01

Speech is metered if the stresses occur at a nearly regular rate. Metered speech is common in poetry, and it can occur naturally in speech, if the speaker is spelling a word or reciting words or numbers from a list. In radio communications, the CQ request, call sign and other codes are frequently metered. In tactical communications and air traffic control, location, heading and identification codes may be metered. Moreover metering may be expected to survive even in HF communications, which are corrupted by noise, interference and mistuning. For this environment, speech recognition and conventional machine-based methods are not effective. We describe Time-Frequency methods which have been adapted successfully to the problem of mitigation of HF signal conditions and detection of metered speech. These methods are based on modeled time and frequency correlation properties of nearly harmonic functions. We derive these properties and demonstrate a performance gain over conventional correlation and spectral methods. Finally, in addressing the problem of HF single sideband (SSB) communications, the problems of carrier mistuning, interfering signals, such as manual Morse, and fast automatic gain control (AGC) must be addressed. We demonstrate simple methods which may be used to blindly mitigate mistuning and narrowband interference, and effectively invert the fast automatic gain function.

Is automatic speech-to-text transcription ready for use in psychological experiments?

PubMed

Ziman, Kirsten; Heusser, Andrew C; Fitzpatrick, Paxton C; Field, Campbell E; Manning, Jeremy R

2018-04-23

Verbal responses are a convenient and naturalistic way for participants to provide data in psychological experiments (Salzinger, The Journal of General Psychology, 61(1),65-94:1959). However, audio recordings of verbal responses typically require additional processing, such as transcribing the recordings into text, as compared with other behavioral response modalities (e.g., typed responses, button presses, etc.). Further, the transcription process is often tedious and time-intensive, requiring human listeners to manually examine each moment of recorded speech. Here we evaluate the performance of a state-of-the-art speech recognition algorithm (Halpern et al., 2016) in transcribing audio data into text during a list-learning experiment. We compare transcripts made by human annotators to the computer-generated transcripts. Both sets of transcripts matched to a high degree and exhibited similar statistical properties, in terms of the participants' recall performance and recall dynamics that the transcripts captured. This proof-of-concept study suggests that speech-to-text engines could provide a cheap, reliable, and rapid means of automatically transcribing speech data in psychological experiments. Further, our findings open the door for verbal response experiments that scale to thousands of participants (e.g., administered online), as well as a new generation of experiments that decode speech on the fly and adapt experimental parameters based on participants' prior responses.

The Contribution of Brainstem and Cerebellar Pathways to Auditory Recognition

PubMed Central

McLachlan, Neil M.; Wilson, Sarah J.

2017-01-01

The cerebellum has been known to play an important role in motor functions for many years. More recently its role has been expanded to include a range of cognitive and sensory-motor processes, and substantial neuroimaging and clinical evidence now points to cerebellar involvement in most auditory processing tasks. In particular, an increase in the size of the cerebellum over recent human evolution has been attributed in part to the development of speech. Despite this, the auditory cognition literature has largely overlooked afferent auditory connections to the cerebellum that have been implicated in acoustically conditioned reflexes in animals, and could subserve speech and other auditory processing in humans. This review expands our understanding of auditory processing by incorporating cerebellar pathways into the anatomy and functions of the human auditory system. We reason that plasticity in the cerebellar pathways underpins implicit learning of spectrotemporal information necessary for sound and speech recognition. Once learnt, this information automatically recognizes incoming auditory signals and predicts likely subsequent information based on previous experience. Since sound recognition processes involving the brainstem and cerebellum initiate early in auditory processing, learnt information stored in cerebellar memory templates could then support a range of auditory processing functions such as streaming, habituation, the integration of auditory feature information such as pitch, and the recognition of vocal communications. PMID:28373850

"Rate My Therapist": Automated Detection of Empathy in Drug and Alcohol Counseling via Speech and Language Processing.

PubMed

Xiao, Bo; Imel, Zac E; Georgiou, Panayiotis G; Atkins, David C; Narayanan, Shrikanth S

2015-01-01

The technology for evaluating patient-provider interactions in psychotherapy-observational coding-has not changed in 70 years. It is labor-intensive, error prone, and expensive, limiting its use in evaluating psychotherapy in the real world. Engineering solutions from speech and language processing provide new methods for the automatic evaluation of provider ratings from session recordings. The primary data are 200 Motivational Interviewing (MI) sessions from a study on MI training methods with observer ratings of counselor empathy. Automatic Speech Recognition (ASR) was used to transcribe sessions, and the resulting words were used in a text-based predictive model of empathy. Two supporting datasets trained the speech processing tasks including ASR (1200 transcripts from heterogeneous psychotherapy sessions and 153 transcripts and session recordings from 5 MI clinical trials). The accuracy of computationally-derived empathy ratings were evaluated against human ratings for each provider. Computationally-derived empathy scores and classifications (high vs. low) were highly accurate against human-based codes and classifications, with a correlation of 0.65 and F-score (a weighted average of sensitivity and specificity) of 0.86, respectively. Empathy prediction using human transcription as input (as opposed to ASR) resulted in a slight increase in prediction accuracies, suggesting that the fully automatic system with ASR is relatively robust. Using speech and language processing methods, it is possible to generate accurate predictions of provider performance in psychotherapy from audio recordings alone. This technology can support large-scale evaluation of psychotherapy for dissemination and process studies.

Separable spectro-temporal Gabor filter bank features: Reducing the complexity of robust features for automatic speech recognition.

PubMed

Schädler, Marc René; Kollmeier, Birger

2015-04-01

To test if simultaneous spectral and temporal processing is required to extract robust features for automatic speech recognition (ASR), the robust spectro-temporal two-dimensional-Gabor filter bank (GBFB) front-end from Schädler, Meyer, and Kollmeier [J. Acoust. Soc. Am. 131, 4134-4151 (2012)] was de-composed into a spectral one-dimensional-Gabor filter bank and a temporal one-dimensional-Gabor filter bank. A feature set that is extracted with these separate spectral and temporal modulation filter banks was introduced, the separate Gabor filter bank (SGBFB) features, and evaluated on the CHiME (Computational Hearing in Multisource Environments) keywords-in-noise recognition task. From the perspective of robust ASR, the results showed that spectral and temporal processing can be performed independently and are not required to interact with each other. Using SGBFB features permitted the signal-to-noise ratio (SNR) to be lowered by 1.2 dB while still performing as well as the GBFB-based reference system, which corresponds to a relative improvement of the word error rate by 12.8%. Additionally, the real time factor of the spectro-temporal processing could be reduced by more than an order of magnitude. Compared to human listeners, the SNR needed to be 13 dB higher when using Mel-frequency cepstral coefficient features, 11 dB higher when using GBFB features, and 9 dB higher when using SGBFB features to achieve the same recognition performance.

The Game Embedded CALL System to Facilitate English Vocabulary Acquisition and Pronunciation

ERIC Educational Resources Information Center

Young, Shelley Shwu-Ching; Wang, Yi-Hsuan

2014-01-01

The aim of this study is to make a new attempt to explore the potential of integrating game strategies with automatic speech recognition technologies to provide learners with individual opportunities for English pronunciation learning. The study developed the Game Embedded CALL (GeCALL) system with two activities for on-line speaking practice. For…

Arabic Language Modeling with Stem-Derived Morphemes for Automatic Speech Recognition

ERIC Educational Resources Information Center

Heintz, Ilana

2010-01-01

The goal of this dissertation is to introduce a method for deriving morphemes from Arabic words using stem patterns, a feature of Arabic morphology. The motivations are three-fold: modeling with morphemes rather than words should help address the out-of-vocabulary problem; working with stem patterns should prove to be a cross-dialectally valid…

A Hybrid Acoustic and Pronunciation Model Adaptation Approach for Non-native Speech Recognition

NASA Astrophysics Data System (ADS)

Oh, Yoo Rhee; Kim, Hong Kook

In this paper, we propose a hybrid model adaptation approach in which pronunciation and acoustic models are adapted by incorporating the pronunciation and acoustic variabilities of non-native speech in order to improve the performance of non-native automatic speech recognition (ASR). Specifically, the proposed hybrid model adaptation can be performed at either the state-tying or triphone-modeling level, depending at which acoustic model adaptation is performed. In both methods, we first analyze the pronunciation variant rules of non-native speakers and then classify each rule as either a pronunciation variant or an acoustic variant. The state-tying level hybrid method then adapts pronunciation models and acoustic models by accommodating the pronunciation variants in the pronunciation dictionary and by clustering the states of triphone acoustic models using the acoustic variants, respectively. On the other hand, the triphone-modeling level hybrid method initially adapts pronunciation models in the same way as in the state-tying level hybrid method; however, for the acoustic model adaptation, the triphone acoustic models are then re-estimated based on the adapted pronunciation models and the states of the re-estimated triphone acoustic models are clustered using the acoustic variants. From the Korean-spoken English speech recognition experiments, it is shown that ASR systems employing the state-tying and triphone-modeling level adaptation methods can relatively reduce the average word error rates (WERs) by 17.1% and 22.1% for non-native speech, respectively, when compared to a baseline ASR system.

Objective Prediction of Hearing Aid Benefit Across Listener Groups Using Machine Learning: Speech Recognition Performance With Binaural Noise-Reduction Algorithms.

PubMed

Schädler, Marc R; Warzybok, Anna; Kollmeier, Birger

2018-01-01

The simulation framework for auditory discrimination experiments (FADE) was adopted and validated to predict the individual speech-in-noise recognition performance of listeners with normal and impaired hearing with and without a given hearing-aid algorithm. FADE uses a simple automatic speech recognizer (ASR) to estimate the lowest achievable speech reception thresholds (SRTs) from simulated speech recognition experiments in an objective way, independent from any empirical reference data. Empirical data from the literature were used to evaluate the model in terms of predicted SRTs and benefits in SRT with the German matrix sentence recognition test when using eight single- and multichannel binaural noise-reduction algorithms. To allow individual predictions of SRTs in binaural conditions, the model was extended with a simple better ear approach and individualized by taking audiograms into account. In a realistic binaural cafeteria condition, FADE explained about 90% of the variance of the empirical SRTs for a group of normal-hearing listeners and predicted the corresponding benefits with a root-mean-square prediction error of 0.6 dB. This highlights the potential of the approach for the objective assessment of benefits in SRT without prior knowledge about the empirical data. The predictions for the group of listeners with impaired hearing explained 75% of the empirical variance, while the individual predictions explained less than 25%. Possibly, additional individual factors should be considered for more accurate predictions with impaired hearing. A competing talker condition clearly showed one limitation of current ASR technology, as the empirical performance with SRTs lower than -20 dB could not be predicted.

Objective Prediction of Hearing Aid Benefit Across Listener Groups Using Machine Learning: Speech Recognition Performance With Binaural Noise-Reduction Algorithms

PubMed Central

Schädler, Marc R.; Warzybok, Anna; Kollmeier, Birger

2018-01-01

The simulation framework for auditory discrimination experiments (FADE) was adopted and validated to predict the individual speech-in-noise recognition performance of listeners with normal and impaired hearing with and without a given hearing-aid algorithm. FADE uses a simple automatic speech recognizer (ASR) to estimate the lowest achievable speech reception thresholds (SRTs) from simulated speech recognition experiments in an objective way, independent from any empirical reference data. Empirical data from the literature were used to evaluate the model in terms of predicted SRTs and benefits in SRT with the German matrix sentence recognition test when using eight single- and multichannel binaural noise-reduction algorithms. To allow individual predictions of SRTs in binaural conditions, the model was extended with a simple better ear approach and individualized by taking audiograms into account. In a realistic binaural cafeteria condition, FADE explained about 90% of the variance of the empirical SRTs for a group of normal-hearing listeners and predicted the corresponding benefits with a root-mean-square prediction error of 0.6 dB. This highlights the potential of the approach for the objective assessment of benefits in SRT without prior knowledge about the empirical data. The predictions for the group of listeners with impaired hearing explained 75% of the empirical variance, while the individual predictions explained less than 25%. Possibly, additional individual factors should be considered for more accurate predictions with impaired hearing. A competing talker condition clearly showed one limitation of current ASR technology, as the empirical performance with SRTs lower than −20 dB could not be predicted. PMID:29692200

Severity-Based Adaptation with Limited Data for ASR to Aid Dysarthric Speakers

PubMed Central

Mustafa, Mumtaz Begum; Salim, Siti Salwah; Mohamed, Noraini; Al-Qatab, Bassam; Siong, Chng Eng

2014-01-01

Automatic speech recognition (ASR) is currently used in many assistive technologies, such as helping individuals with speech impairment in their communication ability. One challenge in ASR for speech-impaired individuals is the difficulty in obtaining a good speech database of impaired speakers for building an effective speech acoustic model. Because there are very few existing databases of impaired speech, which are also limited in size, the obvious solution to build a speech acoustic model of impaired speech is by employing adaptation techniques. However, issues that have not been addressed in existing studies in the area of adaptation for speech impairment are as follows: (1) identifying the most effective adaptation technique for impaired speech; and (2) the use of suitable source models to build an effective impaired-speech acoustic model. This research investigates the above-mentioned two issues on dysarthria, a type of speech impairment affecting millions of people. We applied both unimpaired and impaired speech as the source model with well-known adaptation techniques like the maximum likelihood linear regression (MLLR) and the constrained-MLLR(C-MLLR). The recognition accuracy of each impaired speech acoustic model is measured in terms of word error rate (WER), with further assessments, including phoneme insertion, substitution and deletion rates. Unimpaired speech when combined with limited high-quality speech-impaired data improves performance of ASR systems in recognising severely impaired dysarthric speech. The C-MLLR adaptation technique was also found to be better than MLLR in recognising mildly and moderately impaired speech based on the statistical analysis of the WER. It was found that phoneme substitution was the biggest contributing factor in WER in dysarthric speech for all levels of severity. The results show that the speech acoustic models derived from suitable adaptation techniques improve the performance of ASR systems in recognising impaired speech with limited adaptation data. PMID:24466004

iFER: facial expression recognition using automatically selected geometric eye and eyebrow features

NASA Astrophysics Data System (ADS)

Oztel, Ismail; Yolcu, Gozde; Oz, Cemil; Kazan, Serap; Bunyak, Filiz

2018-03-01

Facial expressions have an important role in interpersonal communications and estimation of emotional states or intentions. Automatic recognition of facial expressions has led to many practical applications and became one of the important topics in computer vision. We present a facial expression recognition system that relies on geometry-based features extracted from eye and eyebrow regions of the face. The proposed system detects keypoints on frontal face images and forms a feature set using geometric relationships among groups of detected keypoints. Obtained feature set is refined and reduced using the sequential forward selection (SFS) algorithm and fed to a support vector machine classifier to recognize five facial expression classes. The proposed system, iFER (eye-eyebrow only facial expression recognition), is robust to lower face occlusions that may be caused by beards, mustaches, scarves, etc. and lower face motion during speech production. Preliminary experiments on benchmark datasets produced promising results outperforming previous facial expression recognition studies using partial face features, and comparable results to studies using whole face information, only slightly lower by ˜ 2.5 % compared to the best whole face facial recognition system while using only ˜ 1 / 3 of the facial region.

A probabilistic union model with automatic order selection for noisy speech recognition.

PubMed

Jancovic, P; Ming, J

2001-09-01

A critical issue in exploiting the potential of the sub-band-based approach to robust speech recognition is the method of combining the sub-band observations, for selecting the bands unaffected by noise. A new method for this purpose, i.e., the probabilistic union model, was recently introduced. This model has been shown to be capable of dealing with band-limited corruption, requiring no knowledge about the band position and statistical distribution of the noise. A parameter within the model, which we call its order, gives the best results when it equals the number of noisy bands. Since this information may not be available in practice, in this paper we introduce an automatic algorithm for selecting the order, based on the state duration pattern generated by the hidden Markov model (HMM). The algorithm has been tested on the TIDIGITS database corrupted by various types of additive band-limited noise with unknown noisy bands. The results have shown that the union model equipped with the new algorithm can achieve a recognition performance similar to that achieved when the number of noisy bands is known. The results show a very significant improvement over the traditional full-band model, without requiring prior information on either the position or the number of noisy bands. The principle of the algorithm for selecting the order based on state duration may also be applied to other sub-band combination methods.

Towards the Development of a Comprehensive Pedagogical Framework for Pronunciation Training Based on Adapted Automatic Speech Recognition Systems

ERIC Educational Resources Information Center

Ali, Saandia

2016-01-01

This paper reports on the early stages of a locally funded research and development project taking place at Rennes 2 university. It aims at developing a comprehensive pedagogical framework for pronunciation training for adult learners of English. This framework will combine a direct approach to pronunciation training (face-to-face teaching) with…

Automatic speech recognition in air-ground data link

NASA Technical Reports Server (NTRS)

Armstrong, Herbert B.

1989-01-01

In the present air traffic system, information presented to the transport aircraft cockpit crew may originate from a variety of sources and may be presented to the crew in visual or aural form, either through cockpit instrument displays or, most often, through voice communication. Voice radio communications are the most error prone method for air-ground data link. Voice messages can be misstated or misunderstood and radio frequency congestion can delay or obscure important messages. To prevent proliferation, a multiplexed data link display can be designed to present information from multiple data link sources on a shared cockpit display unit (CDU) or multi-function display (MFD) or some future combination of flight management and data link information. An aural data link which incorporates an automatic speech recognition (ASR) system for crew response offers several advantages over visual displays. The possibility of applying ASR to the air-ground data link was investigated. The first step was to review current efforts in ASR applications in the cockpit and in air traffic control and evaluated their possible data line application. Next, a series of preliminary research questions is to be developed for possible future collaboration.

"Rate My Therapist": Automated Detection of Empathy in Drug and Alcohol Counseling via Speech and Language Processing

PubMed Central

Xiao, Bo; Imel, Zac E.; Georgiou, Panayiotis G.; Atkins, David C.; Narayanan, Shrikanth S.

2015-01-01

The technology for evaluating patient-provider interactions in psychotherapy–observational coding–has not changed in 70 years. It is labor-intensive, error prone, and expensive, limiting its use in evaluating psychotherapy in the real world. Engineering solutions from speech and language processing provide new methods for the automatic evaluation of provider ratings from session recordings. The primary data are 200 Motivational Interviewing (MI) sessions from a study on MI training methods with observer ratings of counselor empathy. Automatic Speech Recognition (ASR) was used to transcribe sessions, and the resulting words were used in a text-based predictive model of empathy. Two supporting datasets trained the speech processing tasks including ASR (1200 transcripts from heterogeneous psychotherapy sessions and 153 transcripts and session recordings from 5 MI clinical trials). The accuracy of computationally-derived empathy ratings were evaluated against human ratings for each provider. Computationally-derived empathy scores and classifications (high vs. low) were highly accurate against human-based codes and classifications, with a correlation of 0.65 and F-score (a weighted average of sensitivity and specificity) of 0.86, respectively. Empathy prediction using human transcription as input (as opposed to ASR) resulted in a slight increase in prediction accuracies, suggesting that the fully automatic system with ASR is relatively robust. Using speech and language processing methods, it is possible to generate accurate predictions of provider performance in psychotherapy from audio recordings alone. This technology can support large-scale evaluation of psychotherapy for dissemination and process studies. PMID:26630392

Retrieving Tract Variables From Acoustics: A Comparison of Different Machine Learning Strategies.

PubMed

Mitra, Vikramjit; Nam, Hosung; Espy-Wilson, Carol Y; Saltzman, Elliot; Goldstein, Louis

2010-09-13

Many different studies have claimed that articulatory information can be used to improve the performance of automatic speech recognition systems. Unfortunately, such articulatory information is not readily available in typical speaker-listener situations. Consequently, such information has to be estimated from the acoustic signal in a process which is usually termed "speech-inversion." This study aims to propose and compare various machine learning strategies for speech inversion: Trajectory mixture density networks (TMDNs), feedforward artificial neural networks (FF-ANN), support vector regression (SVR), autoregressive artificial neural network (AR-ANN), and distal supervised learning (DSL). Further, using a database generated by the Haskins Laboratories speech production model, we test the claim that information regarding constrictions produced by the distinct organs of the vocal tract (vocal tract variables) is superior to flesh-point information (articulatory pellet trajectories) for the inversion process.

Exploring expressivity and emotion with artificial voice and speech technologies.

PubMed

Pauletto, Sandra; Balentine, Bruce; Pidcock, Chris; Jones, Kevin; Bottaci, Leonardo; Aretoulaki, Maria; Wells, Jez; Mundy, Darren P; Balentine, James

2013-10-01

Emotion in audio-voice signals, as synthesized by text-to-speech (TTS) technologies, was investigated to formulate a theory of expression for user interface design. Emotional parameters were specified with markup tags, and the resulting audio was further modulated with post-processing techniques. Software was then developed to link a selected TTS synthesizer with an automatic speech recognition (ASR) engine, producing a chatbot that could speak and listen. Using these two artificial voice subsystems, investigators explored both artistic and psychological implications of artificial speech emotion. Goals of the investigation were interdisciplinary, with interest in musical composition, augmentative and alternative communication (AAC), commercial voice announcement applications, human-computer interaction (HCI), and artificial intelligence (AI). The work-in-progress points towards an emerging interdisciplinary ontology for artificial voices. As one study output, HCI tools are proposed for future collaboration.

Does the cost function matter in Bayes decision rule?

PubMed

Schlü ter, Ralf; Nussbaum-Thom, Markus; Ney, Hermann

2012-02-01

In many tasks in pattern recognition, such as automatic speech recognition (ASR), optical character recognition (OCR), part-of-speech (POS) tagging, and other string recognition tasks, we are faced with a well-known inconsistency: The Bayes decision rule is usually used to minimize string (symbol sequence) error, whereas, in practice, we want to minimize symbol (word, character, tag, etc.) error. When comparing different recognition systems, we do indeed use symbol error rate as an evaluation measure. The topic of this work is to analyze the relation between string (i.e., 0-1) and symbol error (i.e., metric, integer valued) cost functions in the Bayes decision rule, for which fundamental analytic results are derived. Simple conditions are derived for which the Bayes decision rule with integer-valued metric cost function and with 0-1 cost gives the same decisions or leads to classes with limited cost. The corresponding conditions can be tested with complexity linear in the number of classes. The results obtained do not make any assumption w.r.t. the structure of the underlying distributions or the classification problem. Nevertheless, the general analytic results are analyzed via simulations of string recognition problems with Levenshtein (edit) distance cost function. The results support earlier findings that considerable improvements are to be expected when initial error rates are high.

Processing of speech signals for physical and sensory disabilities.

PubMed Central

Levitt, H

1995-01-01

Assistive technology involving voice communication is used primarily by people who are deaf, hard of hearing, or who have speech and/or language disabilities. It is also used to a lesser extent by people with visual or motor disabilities. A very wide range of devices has been developed for people with hearing loss. These devices can be categorized not only by the modality of stimulation [i.e., auditory, visual, tactile, or direct electrical stimulation of the auditory nerve (auditory-neural)] but also in terms of the degree of speech processing that is used. At least four such categories can be distinguished: assistive devices (a) that are not designed specifically for speech, (b) that take the average characteristics of speech into account, (c) that process articulatory or phonetic characteristics of speech, and (d) that embody some degree of automatic speech recognition. Assistive devices for people with speech and/or language disabilities typically involve some form of speech synthesis or symbol generation for severe forms of language disability. Speech synthesis is also used in text-to-speech systems for sightless persons. Other applications of assistive technology involving voice communication include voice control of wheelchairs and other devices for people with mobility disabilities. Images Fig. 4 PMID:7479816

Processing of Speech Signals for Physical and Sensory Disabilities

NASA Astrophysics Data System (ADS)

Levitt, Harry

1995-10-01

Assistive technology involving voice communication is used primarily by people who are deaf, hard of hearing, or who have speech and/or language disabilities. It is also used to a lesser extent by people with visual or motor disabilities. A very wide range of devices has been developed for people with hearing loss. These devices can be categorized not only by the modality of stimulation [i.e., auditory, visual, tactile, or direct electrical stimulation of the auditory nerve (auditory-neural)] but also in terms of the degree of speech processing that is used. At least four such categories can be distinguished: assistive devices (a) that are not designed specifically for speech, (b) that take the average characteristics of speech into account, (c) that process articulatory or phonetic characteristics of speech, and (d) that embody some degree of automatic speech recognition. Assistive devices for people with speech and/or language disabilities typically involve some form of speech synthesis or symbol generation for severe forms of language disability. Speech synthesis is also used in text-to-speech systems for sightless persons. Other applications of assistive technology involving voice communication include voice control of wheelchairs and other devices for people with mobility disabilities.

A Joint Time-Frequency and Matrix Decomposition Feature Extraction Methodology for Pathological Voice Classification

NASA Astrophysics Data System (ADS)

Ghoraani, Behnaz; Krishnan, Sridhar

2009-12-01

The number of people affected by speech problems is increasing as the modern world places increasing demands on the human voice via mobile telephones, voice recognition software, and interpersonal verbal communications. In this paper, we propose a novel methodology for automatic pattern classification of pathological voices. The main contribution of this paper is extraction of meaningful and unique features using Adaptive time-frequency distribution (TFD) and nonnegative matrix factorization (NMF). We construct Adaptive TFD as an effective signal analysis domain to dynamically track the nonstationarity in the speech and utilize NMF as a matrix decomposition (MD) technique to quantify the constructed TFD. The proposed method extracts meaningful and unique features from the joint TFD of the speech, and automatically identifies and measures the abnormality of the signal. Depending on the abnormality measure of each signal, we classify the signal into normal or pathological. The proposed method is applied on the Massachusetts Eye and Ear Infirmary (MEEI) voice disorders database which consists of 161 pathological and 51 normal speakers, and an overall classification accuracy of 98.6% was achieved.

Analysis of Documentation Speed Using Web-Based Medical Speech Recognition Technology: Randomized Controlled Trial.

PubMed

Vogel, Markus; Kaisers, Wolfgang; Wassmuth, Ralf; Mayatepek, Ertan

2015-11-03

Clinical documentation has undergone a change due to the usage of electronic health records. The core element is to capture clinical findings and document therapy electronically. Health care personnel spend a significant portion of their time on the computer. Alternatives to self-typing, such as speech recognition, are currently believed to increase documentation efficiency and quality, as well as satisfaction of health professionals while accomplishing clinical documentation, but few studies in this area have been published to date. This study describes the effects of using a Web-based medical speech recognition system for clinical documentation in a university hospital on (1) documentation speed, (2) document length, and (3) physician satisfaction. Reports of 28 physicians were randomized to be created with (intervention) or without (control) the assistance of a Web-based system of medical automatic speech recognition (ASR) in the German language. The documentation was entered into a browser's text area and the time to complete the documentation including all necessary corrections, correction effort, number of characters, and mood of participant were stored in a database. The underlying time comprised text entering, text correction, and finalization of the documentation event. Participants self-assessed their moods on a scale of 1-3 (1=good, 2=moderate, 3=bad). Statistical analysis was done using permutation tests. The number of clinical reports eligible for further analysis stood at 1455. Out of 1455 reports, 718 (49.35%) were assisted by ASR and 737 (50.65%) were not assisted by ASR. Average documentation speed without ASR was 173 (SD 101) characters per minute, while it was 217 (SD 120) characters per minute using ASR. The overall increase in documentation speed through Web-based ASR assistance was 26% (P=.04). Participants documented an average of 356 (SD 388) characters per report when not assisted by ASR and 649 (SD 561) characters per report when assisted by ASR. Participants' average mood rating was 1.3 (SD 0.6) using ASR assistance compared to 1.6 (SD 0.7) without ASR assistance (P<.001). We conclude that medical documentation with the assistance of Web-based speech recognition leads to an increase in documentation speed, document length, and participant mood when compared to self-typing. Speech recognition is a meaningful and effective tool for the clinical documentation process.

Multi-stream LSTM-HMM decoding and histogram equalization for noise robust keyword spotting.

PubMed

Wöllmer, Martin; Marchi, Erik; Squartini, Stefano; Schuller, Björn

2011-09-01

Highly spontaneous, conversational, and potentially emotional and noisy speech is known to be a challenge for today's automatic speech recognition (ASR) systems, which highlights the need for advanced algorithms that improve speech features and models. Histogram Equalization is an efficient method to reduce the mismatch between clean and noisy conditions by normalizing all moments of the probability distribution of the feature vector components. In this article, we propose to combine histogram equalization and multi-condition training for robust keyword detection in noisy speech. To better cope with conversational speaking styles, we show how contextual information can be effectively exploited in a multi-stream ASR framework that dynamically models context-sensitive phoneme estimates generated by a long short-term memory neural network. The proposed techniques are evaluated on the SEMAINE database-a corpus containing emotionally colored conversations with a cognitive system for "Sensitive Artificial Listening".

Perception and performance in flight simulators: The contribution of vestibular, visual, and auditory information

NASA Technical Reports Server (NTRS)

1979-01-01

The pilot's perception and performance in flight simulators is examined. The areas investigated include: vestibular stimulation, flight management and man cockpit information interfacing, and visual perception in flight simulation. The effects of higher levels of rotary acceleration on response time to constant acceleration, tracking performance, and thresholds for angular acceleration are examined. Areas of flight management examined are cockpit display of traffic information, work load, synthetic speech call outs during the landing phase of flight, perceptual factors in the use of a microwave landing system, automatic speech recognition, automation of aircraft operation, and total simulation of flight training.

Phonologically-based biomarkers for major depressive disorder

NASA Astrophysics Data System (ADS)

Trevino, Andrea Carolina; Quatieri, Thomas Francis; Malyska, Nicolas

2011-12-01

Of increasing importance in the civilian and military population is the recognition of major depressive disorder at its earliest stages and intervention before the onset of severe symptoms. Toward the goal of more effective monitoring of depression severity, we introduce vocal biomarkers that are derived automatically from phonologically-based measures of speech rate. To assess our measures, we use a 35-speaker free-response speech database of subjects treated for depression over a 6-week duration. We find that dissecting average measures of speech rate into phone-specific characteristics and, in particular, combined phone-duration measures uncovers stronger relationships between speech rate and depression severity than global measures previously reported for a speech-rate biomarker. Results of this study are supported by correlation of our measures with depression severity and classification of depression state with these vocal measures. Our approach provides a general framework for analyzing individual symptom categories through phonological units, and supports the premise that speaking rate can be an indicator of psychomotor retardation severity.

The transition to increased automaticity during finger sequence learning in adult males who stutter.

PubMed

Smits-Bandstra, Sarah; De Nil, Luc; Rochon, Elizabeth

2006-01-01

The present study compared the automaticity levels of persons who stutter (PWS) and persons who do not stutter (PNS) on a practiced finger sequencing task under dual task conditions. Automaticity was defined as the amount of attention required for task performance. Twelve PWS and 12 control subjects practiced finger tapping sequences under single and then dual task conditions. Control subjects performed the sequencing task significantly faster and less variably under single versus dual task conditions while PWS' performance was consistently slow and variable (comparable to the dual task performance of control subjects) under both conditions. Control subjects were significantly more accurate on a colour recognition distracter task than PWS under dual task conditions. These results suggested that control subjects transitioned to quick, accurate and increasingly automatic performance on the sequencing task after practice, while PWS did not. Because most stuttering treatment programs for adults include practice and automatization of new motor speech skills, findings of this finger sequencing study and future studies of speech sequence learning may have important implications for how to maximize stuttering treatment effectiveness. As a result of this activity, the participant will be able to: (1) Define automaticity and explain the importance of dual task paradigms to investigate automaticity; (2) Relate the proposed relationship between motor learning and automaticity as stated by the authors; (3) Summarize the reviewed literature concerning the performance of PWS on dual tasks; and (4) Explain why the ability to transition to automaticity during motor learning may have important clinical implications for stuttering treatment effectiveness.

Hands-free human-machine interaction with voice

NASA Astrophysics Data System (ADS)

Juang, B. H.

2004-05-01

Voice is natural communication interface between a human and a machine. The machine, when placed in today's communication networks, may be configured to provide automation to save substantial operating cost, as demonstrated in AT&T's VRCP (Voice Recognition Call Processing), or to facilitate intelligent services, such as virtual personal assistants, to enhance individual productivity. These intelligent services often need to be accessible anytime, anywhere (e.g., in cars when the user is in a hands-busy-eyes-busy situation or during meetings where constantly talking to a microphone is either undersirable or impossible), and thus call for advanced signal processing and automatic speech recognition techniques which support what we call ``hands-free'' human-machine communication. These techniques entail a broad spectrum of technical ideas, ranging from use of directional microphones and acoustic echo cancellatiion to robust speech recognition. In this talk, we highlight a number of key techniques that were developed for hands-free human-machine communication in the mid-1990s after Bell Labs became a unit of Lucent Technologies. A video clip will be played to demonstrate the accomplishement.

Fifty years of progress in speech and speaker recognition

NASA Astrophysics Data System (ADS)

Furui, Sadaoki

2004-10-01

Speech and speaker recognition technology has made very significant progress in the past 50 years. The progress can be summarized by the following changes: (1) from template matching to corpus-base statistical modeling, e.g., HMM and n-grams, (2) from filter bank/spectral resonance to Cepstral features (Cepstrum + DCepstrum + DDCepstrum), (3) from heuristic time-normalization to DTW/DP matching, (4) from gdistanceh-based to likelihood-based methods, (5) from maximum likelihood to discriminative approach, e.g., MCE/GPD and MMI, (6) from isolated word to continuous speech recognition, (7) from small vocabulary to large vocabulary recognition, (8) from context-independent units to context-dependent units for recognition, (9) from clean speech to noisy/telephone speech recognition, (10) from single speaker to speaker-independent/adaptive recognition, (11) from monologue to dialogue/conversation recognition, (12) from read speech to spontaneous speech recognition, (13) from recognition to understanding, (14) from single-modality (audio signal only) to multi-modal (audio/visual) speech recognition, (15) from hardware recognizer to software recognizer, and (16) from no commercial application to many practical commercial applications. Most of these advances have taken place in both the fields of speech recognition and speaker recognition. The majority of technological changes have been directed toward the purpose of increasing robustness of recognition, including many other additional important techniques not noted above.

What’s Wrong With Automatic Speech Recognition (ASR) and How Can We Fix It?

DTIC Science & Technology

2013-03-01

Jordan Cohen International Computer Science Institute 1947 Center Street, Suite 600 Berkeley, CA 94704 MARCH 2013 Final Report ...This report was cleared for public release by the 88th Air Base Wing Public Affairs Office and is available to the general public, including foreign...711th Human Performance Wing Air Force Research Laboratory This report is published in the interest of scientific and technical

Age-Related Differences in Lexical Access Relate to Speech Recognition in Noise

PubMed Central

Carroll, Rebecca; Warzybok, Anna; Kollmeier, Birger; Ruigendijk, Esther

2016-01-01

Vocabulary size has been suggested as a useful measure of “verbal abilities” that correlates with speech recognition scores. Knowing more words is linked to better speech recognition. How vocabulary knowledge translates to general speech recognition mechanisms, how these mechanisms relate to offline speech recognition scores, and how they may be modulated by acoustical distortion or age, is less clear. Age-related differences in linguistic measures may predict age-related differences in speech recognition in noise performance. We hypothesized that speech recognition performance can be predicted by the efficiency of lexical access, which refers to the speed with which a given word can be searched and accessed relative to the size of the mental lexicon. We tested speech recognition in a clinical German sentence-in-noise test at two signal-to-noise ratios (SNRs), in 22 younger (18–35 years) and 22 older (60–78 years) listeners with normal hearing. We also assessed receptive vocabulary, lexical access time, verbal working memory, and hearing thresholds as measures of individual differences. Age group, SNR level, vocabulary size, and lexical access time were significant predictors of individual speech recognition scores, but working memory and hearing threshold were not. Interestingly, longer accessing times were correlated with better speech recognition scores. Hierarchical regression models for each subset of age group and SNR showed very similar patterns: the combination of vocabulary size and lexical access time contributed most to speech recognition performance; only for the younger group at the better SNR (yielding about 85% correct speech recognition) did vocabulary size alone predict performance. Our data suggest that successful speech recognition in noise is mainly modulated by the efficiency of lexical access. This suggests that older adults’ poorer performance in the speech recognition task may have arisen from reduced efficiency in lexical access; with an average vocabulary size similar to that of younger adults, they were still slower in lexical access. PMID:27458400

Age-Related Differences in Lexical Access Relate to Speech Recognition in Noise.

PubMed

Carroll, Rebecca; Warzybok, Anna; Kollmeier, Birger; Ruigendijk, Esther

2016-01-01

Vocabulary size has been suggested as a useful measure of "verbal abilities" that correlates with speech recognition scores. Knowing more words is linked to better speech recognition. How vocabulary knowledge translates to general speech recognition mechanisms, how these mechanisms relate to offline speech recognition scores, and how they may be modulated by acoustical distortion or age, is less clear. Age-related differences in linguistic measures may predict age-related differences in speech recognition in noise performance. We hypothesized that speech recognition performance can be predicted by the efficiency of lexical access, which refers to the speed with which a given word can be searched and accessed relative to the size of the mental lexicon. We tested speech recognition in a clinical German sentence-in-noise test at two signal-to-noise ratios (SNRs), in 22 younger (18-35 years) and 22 older (60-78 years) listeners with normal hearing. We also assessed receptive vocabulary, lexical access time, verbal working memory, and hearing thresholds as measures of individual differences. Age group, SNR level, vocabulary size, and lexical access time were significant predictors of individual speech recognition scores, but working memory and hearing threshold were not. Interestingly, longer accessing times were correlated with better speech recognition scores. Hierarchical regression models for each subset of age group and SNR showed very similar patterns: the combination of vocabulary size and lexical access time contributed most to speech recognition performance; only for the younger group at the better SNR (yielding about 85% correct speech recognition) did vocabulary size alone predict performance. Our data suggest that successful speech recognition in noise is mainly modulated by the efficiency of lexical access. This suggests that older adults' poorer performance in the speech recognition task may have arisen from reduced efficiency in lexical access; with an average vocabulary size similar to that of younger adults, they were still slower in lexical access.

[Design and implementation of mobile terminal data acquisition for Chinese materia medica resources survey].

PubMed

Qi, Yuan-Hua; Wang, Hui; Zhang, Xiao-Bo; Jin, Yan; Ge, Xiao-Guang; Jing, Zhi-Xian; Wang, Ling; Zhao, Yu-Ping; Guo, Lan-Ping; Huang, Lu-Qi

2017-11-01

In this paper, a data acquisition system based on mobile terminal combining GPS, offset correction, automatic speech recognition and database networking technology was designed implemented with the function of locating the latitude and elevation information fast, taking conveniently various types of Chinese herbal plant photos, photos, samples habitat photos and so on. The mobile system realizes automatic association with Chinese medicine source information, through the voice recognition function it records the information of plant characteristics and environmental characteristics, and record relevant plant specimen information. The data processing platform based on Chinese medicine resources survey data reporting client can effectively assists in indoor data processing, derives the mobile terminal data to computer terminal. The established data acquisition system provides strong technical support for the fourth national survey of the Chinese materia medica resources (CMMR). Copyright© by the Chinese Pharmaceutical Association.

Should visual speech cues (speechreading) be considered when fitting hearing aids?

NASA Astrophysics Data System (ADS)

Grant, Ken

2002-05-01

When talker and listener are face-to-face, visual speech cues become an important part of the communication environment, and yet, these cues are seldom considered when designing hearing aids. Models of auditory-visual speech recognition highlight the importance of complementary versus redundant speech information for predicting auditory-visual recognition performance. Thus, for hearing aids to work optimally when visual speech cues are present, it is important to know whether the cues provided by amplification and the cues provided by speechreading complement each other. In this talk, data will be reviewed that show nonmonotonicity between auditory-alone speech recognition and auditory-visual speech recognition, suggesting that efforts designed solely to improve auditory-alone recognition may not always result in improved auditory-visual recognition. Data will also be presented showing that one of the most important speech cues for enhancing auditory-visual speech recognition performance, voicing, is often the cue that benefits least from amplification.

SAM: speech-aware applications in medicine to support structured data entry.

PubMed Central

Wormek, A. K.; Ingenerf, J.; Orthner, H. F.

1997-01-01

In the last two years, improvement in speech recognition technology has directed the medical community's interest to porting and using such innovations in clinical systems. The acceptance of speech recognition systems in clinical domains increases with recognition speed, large medical vocabulary, high accuracy, continuous speech recognition, and speaker independence. Although some commercial speech engines approach these requirements, the greatest benefit can be achieved in adapting a speech recognizer to a specific medical application. The goals of our work are first, to develop a speech-aware core component which is able to establish connections to speech recognition engines of different vendors. This is realized in SAM. Second, with applications based on SAM we want to support the physician in his/her routine clinical care activities. Within the STAMP project (STAndardized Multimedia report generator in Pathology), we extend SAM by combining a structured data entry approach with speech recognition technology. Another speech-aware application in the field of Diabetes care is connected to a terminology server. The server delivers a controlled vocabulary which can be used for speech recognition. PMID:9357730

Voice-processing technologies--their application in telecommunications.

PubMed Central

Wilpon, J G

1995-01-01

As the telecommunications industry evolves over the next decade to provide the products and services that people will desire, several key technologies will become commonplace. Two of these, automatic speech recognition and text-to-speech synthesis, will provide users with more freedom on when, where, and how they access information. While these technologies are currently in their infancy, their capabilities are rapidly increasing and their deployment in today's telephone network is expanding. The economic impact of just one application, the automation of operator services, is well over $100 million per year. Yet there still are many technical challenges that must be resolved before these technologies can be deployed ubiquitously in products and services throughout the worldwide telephone network. These challenges include: (i) High level of accuracy. The technology must be perceived by the user as highly accurate, robust, and reliable. (ii) Easy to use. Speech is only one of several possible input/output modalities for conveying information between a human and a machine, much like a computer terminal or Touch-Tone pad on a telephone. It is not the final product. Therefore, speech technologies must be hidden from the user. That is, the burden of using the technology must be on the technology itself. (iii) Quick prototyping and development of new products and services. The technology must support the creation of new products and services based on speech in an efficient and timely fashion. In this paper I present a vision of the voice-processing industry with a focus on the areas with the broadest base of user penetration: speech recognition, text-to-speech synthesis, natural language processing, and speaker recognition technologies. The current and future applications of these technologies in the telecommunications industry will be examined in terms of their strengths, limitations, and the degree to which user needs have been or have yet to be met. Although noteworthy gains have been made in areas with potentially small user bases and in the more mature speech-coding technologies, these subjects are outside the scope of this paper. Images Fig. 1 PMID:7479815

Multilingual Vocabularies in Automatic Speech Recognition

DTIC Science & Technology

2000-08-01

monolingual (a few thousands) is an obstacle to a full generalization of the inventories, then moved to the multilingual case. In the approach towards the...direction of language independence. In this monolingual experiment, we developed two types of unit sets for paper, we extend the method presented in [3...sound ji is not assimilated 3.2.1 Monolingual experiments to the corresponding sound in Spanish, but it is left apart as a The baseline model for English

Content-based TV sports video retrieval using multimodal analysis

NASA Astrophysics Data System (ADS)

Yu, Yiqing; Liu, Huayong; Wang, Hongbin; Zhou, Dongru

2003-09-01

In this paper, we propose content-based video retrieval, which is a kind of retrieval by its semantical contents. Because video data is composed of multimodal information streams such as video, auditory and textual streams, we describe a strategy of using multimodal analysis for automatic parsing sports video. The paper first defines the basic structure of sports video database system, and then introduces a new approach that integrates visual stream analysis, speech recognition, speech signal processing and text extraction to realize video retrieval. The experimental results for TV sports video of football games indicate that the multimodal analysis is effective for video retrieval by quickly browsing tree-like video clips or inputting keywords within predefined domain.

Speech recognition technology: an outlook for human-to-machine interaction.

PubMed

Erdel, T; Crooks, S

2000-01-01

Speech recognition, as an enabling technology in healthcare-systems computing, is a topic that has been discussed for quite some time, but is just now coming to fruition. Traditionally, speech-recognition software has been constrained by hardware, but improved processors and increased memory capacities are starting to remove some of these limitations. With these barriers removed, companies that create software for the healthcare setting have the opportunity to write more successful applications. Among the criticisms of speech-recognition applications are the high rates of error and steep training curves. However, even in the face of such negative perceptions, there remains significant opportunities for speech recognition to allow healthcare providers and, more specifically, physicians, to work more efficiently and ultimately spend more time with their patients and less time completing necessary documentation. This article will identify opportunities for inclusion of speech-recognition technology in the healthcare setting and examine major categories of speech-recognition software--continuous speech recognition, command and control, and text-to-speech. We will discuss the advantages and disadvantages of each area, the limitations of the software today, and how future trends might affect them.

Study of acoustic correlates associate with emotional speech

NASA Astrophysics Data System (ADS)

Yildirim, Serdar; Lee, Sungbok; Lee, Chul Min; Bulut, Murtaza; Busso, Carlos; Kazemzadeh, Ebrahim; Narayanan, Shrikanth

2004-10-01

This study investigates the acoustic characteristics of four different emotions expressed in speech. The aim is to obtain detailed acoustic knowledge on how a speech signal is modulated by changes from neutral to a certain emotional state. Such knowledge is necessary for automatic emotion recognition and classification and emotional speech synthesis. Speech data obtained from two semi-professional actresses are analyzed and compared. Each subject produces 211 sentences with four different emotions; neutral, sad, angry, happy. We analyze changes in temporal and acoustic parameters such as magnitude and variability of segmental duration, fundamental frequency and the first three formant frequencies as a function of emotion. Acoustic differences among the emotions are also explored with mutual information computation, multidimensional scaling and acoustic likelihood comparison with normal speech. Results indicate that speech associated with anger and happiness is characterized by longer duration, shorter interword silence, higher pitch and rms energy with wider ranges. Sadness is distinguished from other emotions by lower rms energy and longer interword silence. Interestingly, the difference in formant pattern between [happiness/anger] and [neutral/sadness] are better reflected in back vowels such as /a/(/father/) than in front vowels. Detailed results on intra- and interspeaker variability will be reported.

Relationship between listeners' nonnative speech recognition and categorization abilities

PubMed Central

Atagi, Eriko; Bent, Tessa

2015-01-01

Enhancement of the perceptual encoding of talker characteristics (indexical information) in speech can facilitate listeners' recognition of linguistic content. The present study explored this indexical-linguistic relationship in nonnative speech processing by examining listeners' performance on two tasks: nonnative accent categorization and nonnative speech-in-noise recognition. Results indicated substantial variability across listeners in their performance on both the accent categorization and nonnative speech recognition tasks. Moreover, listeners' accent categorization performance correlated with their nonnative speech-in-noise recognition performance. These results suggest that having more robust indexical representations for nonnative accents may allow listeners to more accurately recognize the linguistic content of nonnative speech. PMID:25618098

Method and apparatus for obtaining complete speech signals for speech recognition applications

NASA Technical Reports Server (NTRS)

Abrash, Victor (Inventor); Cesari, Federico (Inventor); Franco, Horacio (Inventor); George, Christopher (Inventor); Zheng, Jing (Inventor)

2009-01-01

The present invention relates to a method and apparatus for obtaining complete speech signals for speech recognition applications. In one embodiment, the method continuously records an audio stream comprising a sequence of frames to a circular buffer. When a user command to commence or terminate speech recognition is received, the method obtains a number of frames of the audio stream occurring before or after the user command in order to identify an augmented audio signal for speech recognition processing. In further embodiments, the method analyzes the augmented audio signal in order to locate starting and ending speech endpoints that bound at least a portion of speech to be processed for recognition. At least one of the speech endpoints is located using a Hidden Markov Model.

The development of the Athens Emotional States Inventory (AESI): collection, validation and automatic processing of emotionally loaded sentences.

PubMed

Chaspari, Theodora; Soldatos, Constantin; Maragos, Petros

2015-01-01

The development of ecologically valid procedures for collecting reliable and unbiased emotional data towards computer interfaces with social and affective intelligence targeting patients with mental disorders. Following its development, presented with, the Athens Emotional States Inventory (AESI) proposes the design, recording and validation of an audiovisual database for five emotional states: anger, fear, joy, sadness and neutral. The items of the AESI consist of sentences each having content indicative of the corresponding emotion. Emotional content was assessed through a survey of 40 young participants with a questionnaire following the Latin square design. The emotional sentences that were correctly identified by 85% of the participants were recorded in a soundproof room with microphones and cameras. A preliminary validation of AESI is performed through automatic emotion recognition experiments from speech. The resulting database contains 696 recorded utterances in Greek language by 20 native speakers and has a total duration of approximately 28 min. Speech classification results yield accuracy up to 75.15% for automatically recognizing the emotions in AESI. These results indicate the usefulness of our approach for collecting emotional data with reliable content, balanced across classes and with reduced environmental variability.

Temporal Sensitivity Measured Shortly After Cochlear Implantation Predicts 6-Month Speech Recognition Outcome.

PubMed

Erb, Julia; Ludwig, Alexandra Annemarie; Kunke, Dunja; Fuchs, Michael; Obleser, Jonas

2018-04-24

Psychoacoustic tests assessed shortly after cochlear implantation are useful predictors of the rehabilitative speech outcome. While largely independent, both spectral and temporal resolution tests are important to provide an accurate prediction of speech recognition. However, rapid tests of temporal sensitivity are currently lacking. Here, we propose a simple amplitude modulation rate discrimination (AMRD) paradigm that is validated by predicting future speech recognition in adult cochlear implant (CI) patients. In 34 newly implanted patients, we used an adaptive AMRD paradigm, where broadband noise was modulated at the speech-relevant rate of ~4 Hz. In a longitudinal study, speech recognition in quiet was assessed using the closed-set Freiburger number test shortly after cochlear implantation (t0) as well as the open-set Freiburger monosyllabic word test 6 months later (t6). Both AMRD thresholds at t0 (r = -0.51) and speech recognition scores at t0 (r = 0.56) predicted speech recognition scores at t6. However, AMRD and speech recognition at t0 were uncorrelated, suggesting that those measures capture partially distinct perceptual abilities. A multiple regression model predicting 6-month speech recognition outcome with deafness duration and speech recognition at t0 improved from adjusted R = 0.30 to adjusted R = 0.44 when AMRD threshold was added as a predictor. These findings identify AMRD thresholds as a reliable, nonredundant predictor above and beyond established speech tests for CI outcome. This AMRD test could potentially be developed into a rapid clinical temporal-resolution test to be integrated into the postoperative test battery to improve the reliability of speech outcome prognosis.

Structuring Broadcast Audio for Information Access

NASA Astrophysics Data System (ADS)

Gauvain, Jean-Luc; Lamel, Lori

2003-12-01

One rapidly expanding application area for state-of-the-art speech recognition technology is the automatic processing of broadcast audiovisual data for information access. Since much of the linguistic information is found in the audio channel, speech recognition is a key enabling technology which, when combined with information retrieval techniques, can be used for searching large audiovisual document collections. Audio indexing must take into account the specificities of audio data such as needing to deal with the continuous data stream and an imperfect word transcription. Other important considerations are dealing with language specificities and facilitating language portability. At Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur (LIMSI), broadcast news transcription systems have been developed for seven languages: English, French, German, Mandarin, Portuguese, Spanish, and Arabic. The transcription systems have been integrated into prototype demonstrators for several application areas such as audio data mining, structuring audiovisual archives, selective dissemination of information, and topic tracking for media monitoring. As examples, this paper addresses the spoken document retrieval and topic tracking tasks.

Study of wavelet packet energy entropy for emotion classification in speech and glottal signals

NASA Astrophysics Data System (ADS)

He, Ling; Lech, Margaret; Zhang, Jing; Ren, Xiaomei; Deng, Lihua

2013-07-01

The automatic speech emotion recognition has important applications in human-machine communication. Majority of current research in this area is focused on finding optimal feature parameters. In recent studies, several glottal features were examined as potential cues for emotion differentiation. In this study, a new type of feature parameter is proposed, which calculates energy entropy on values within selected Wavelet Packet frequency bands. The modeling and classification tasks are conducted using the classical GMM algorithm. The experiments use two data sets: the Speech Under Simulated Emotion (SUSE) data set annotated with three different emotions (angry, neutral and soft) and Berlin Emotional Speech (BES) database annotated with seven different emotions (angry, bored, disgust, fear, happy, sad and neutral). The average classification accuracy achieved for the SUSE data (74%-76%) is significantly higher than the accuracy achieved for the BES data (51%-54%). In both cases, the accuracy was significantly higher than the respective random guessing levels (33% for SUSE and 14.3% for BES).

Audibility-based predictions of speech recognition for children and adults with normal hearing.

PubMed

McCreery, Ryan W; Stelmachowicz, Patricia G

2011-12-01

This study investigated the relationship between audibility and predictions of speech recognition for children and adults with normal hearing. The Speech Intelligibility Index (SII) is used to quantify the audibility of speech signals and can be applied to transfer functions to predict speech recognition scores. Although the SII is used clinically with children, relatively few studies have evaluated SII predictions of children's speech recognition directly. Children have required more audibility than adults to reach maximum levels of speech understanding in previous studies. Furthermore, children may require greater bandwidth than adults for optimal speech understanding, which could influence frequency-importance functions used to calculate the SII. Speech recognition was measured for 116 children and 19 adults with normal hearing. Stimulus bandwidth and background noise level were varied systematically in order to evaluate speech recognition as predicted by the SII and derive frequency-importance functions for children and adults. Results suggested that children required greater audibility to reach the same level of speech understanding as adults. However, differences in performance between adults and children did not vary across frequency bands. © 2011 Acoustical Society of America

Individual differences in language and working memory affect children's speech recognition in noise.

PubMed

McCreery, Ryan W; Spratford, Meredith; Kirby, Benjamin; Brennan, Marc

2017-05-01

We examined how cognitive and linguistic skills affect speech recognition in noise for children with normal hearing. Children with better working memory and language abilities were expected to have better speech recognition in noise than peers with poorer skills in these domains. As part of a prospective, cross-sectional study, children with normal hearing completed speech recognition in noise for three types of stimuli: (1) monosyllabic words, (2) syntactically correct but semantically anomalous sentences and (3) semantically and syntactically anomalous word sequences. Measures of vocabulary, syntax and working memory were used to predict individual differences in speech recognition in noise. Ninety-six children with normal hearing, who were between 5 and 12 years of age. Higher working memory was associated with better speech recognition in noise for all three stimulus types. Higher vocabulary abilities were associated with better recognition in noise for sentences and word sequences, but not for words. Working memory and language both influence children's speech recognition in noise, but the relationships vary across types of stimuli. These findings suggest that clinical assessment of speech recognition is likely to reflect underlying cognitive and linguistic abilities, in addition to a child's auditory skills, consistent with the Ease of Language Understanding model.

Machine Translation from Text

NASA Astrophysics Data System (ADS)

Habash, Nizar; Olive, Joseph; Christianson, Caitlin; McCary, John

Machine translation (MT) from text, the topic of this chapter, is perhaps the heart of the GALE project. Beyond being a well defined application that stands on its own, MT from text is the link between the automatic speech recognition component and the distillation component. The focus of MT in GALE is on translating from Arabic or Chinese to English. The three languages represent a wide range of linguistic diversity and make the GALE MT task rather challenging and exciting.

pyAudioAnalysis: An Open-Source Python Library for Audio Signal Analysis.

PubMed

Giannakopoulos, Theodoros

2015-01-01

Audio information plays a rather important role in the increasing digital content that is available today, resulting in a need for methodologies that automatically analyze such content: audio event recognition for home automations and surveillance systems, speech recognition, music information retrieval, multimodal analysis (e.g. audio-visual analysis of online videos for content-based recommendation), etc. This paper presents pyAudioAnalysis, an open-source Python library that provides a wide range of audio analysis procedures including: feature extraction, classification of audio signals, supervised and unsupervised segmentation and content visualization. pyAudioAnalysis is licensed under the Apache License and is available at GitHub (https://github.com/tyiannak/pyAudioAnalysis/). Here we present the theoretical background behind the wide range of the implemented methodologies, along with evaluation metrics for some of the methods. pyAudioAnalysis has been already used in several audio analysis research applications: smart-home functionalities through audio event detection, speech emotion recognition, depression classification based on audio-visual features, music segmentation, multimodal content-based movie recommendation and health applications (e.g. monitoring eating habits). The feedback provided from all these particular audio applications has led to practical enhancement of the library.

pyAudioAnalysis: An Open-Source Python Library for Audio Signal Analysis

PubMed Central

Giannakopoulos, Theodoros

2015-01-01

Audio information plays a rather important role in the increasing digital content that is available today, resulting in a need for methodologies that automatically analyze such content: audio event recognition for home automations and surveillance systems, speech recognition, music information retrieval, multimodal analysis (e.g. audio-visual analysis of online videos for content-based recommendation), etc. This paper presents pyAudioAnalysis, an open-source Python library that provides a wide range of audio analysis procedures including: feature extraction, classification of audio signals, supervised and unsupervised segmentation and content visualization. pyAudioAnalysis is licensed under the Apache License and is available at GitHub (https://github.com/tyiannak/pyAudioAnalysis/). Here we present the theoretical background behind the wide range of the implemented methodologies, along with evaluation metrics for some of the methods. pyAudioAnalysis has been already used in several audio analysis research applications: smart-home functionalities through audio event detection, speech emotion recognition, depression classification based on audio-visual features, music segmentation, multimodal content-based movie recommendation and health applications (e.g. monitoring eating habits). The feedback provided from all these particular audio applications has led to practical enhancement of the library. PMID:26656189

Brain-to-text: decoding spoken phrases from phone representations in the brain.

PubMed

Herff, Christian; Heger, Dominic; de Pesters, Adriana; Telaar, Dominic; Brunner, Peter; Schalk, Gerwin; Schultz, Tanja

2015-01-01

It has long been speculated whether communication between humans and machines based on natural speech related cortical activity is possible. Over the past decade, studies have suggested that it is feasible to recognize isolated aspects of speech from neural signals, such as auditory features, phones or one of a few isolated words. However, until now it remained an unsolved challenge to decode continuously spoken speech from the neural substrate associated with speech and language processing. Here, we show for the first time that continuously spoken speech can be decoded into the expressed words from intracranial electrocorticographic (ECoG) recordings.Specifically, we implemented a system, which we call Brain-To-Text that models single phones, employs techniques from automatic speech recognition (ASR), and thereby transforms brain activity while speaking into the corresponding textual representation. Our results demonstrate that our system can achieve word error rates as low as 25% and phone error rates below 50%. Additionally, our approach contributes to the current understanding of the neural basis of continuous speech production by identifying those cortical regions that hold substantial information about individual phones. In conclusion, the Brain-To-Text system described in this paper represents an important step toward human-machine communication based on imagined speech.

Brain-to-text: decoding spoken phrases from phone representations in the brain

PubMed Central

Herff, Christian; Heger, Dominic; de Pesters, Adriana; Telaar, Dominic; Brunner, Peter; Schalk, Gerwin; Schultz, Tanja

2015-01-01

It has long been speculated whether communication between humans and machines based on natural speech related cortical activity is possible. Over the past decade, studies have suggested that it is feasible to recognize isolated aspects of speech from neural signals, such as auditory features, phones or one of a few isolated words. However, until now it remained an unsolved challenge to decode continuously spoken speech from the neural substrate associated with speech and language processing. Here, we show for the first time that continuously spoken speech can be decoded into the expressed words from intracranial electrocorticographic (ECoG) recordings.Specifically, we implemented a system, which we call Brain-To-Text that models single phones, employs techniques from automatic speech recognition (ASR), and thereby transforms brain activity while speaking into the corresponding textual representation. Our results demonstrate that our system can achieve word error rates as low as 25% and phone error rates below 50%. Additionally, our approach contributes to the current understanding of the neural basis of continuous speech production by identifying those cortical regions that hold substantial information about individual phones. In conclusion, the Brain-To-Text system described in this paper represents an important step toward human-machine communication based on imagined speech. PMID:26124702

Speech systems research at Texas Instruments

NASA Technical Reports Server (NTRS)

Doddington, George R.

1977-01-01

An assessment of automatic speech processing technology is presented. Fundamental problems in the development and the deployment of automatic speech processing systems are defined and a technology forecast for speech systems is presented.

An Innovative Speech-Based User Interface for Smarthomes and IoT Solutions to Help People with Speech and Motor Disabilities.

PubMed

Malavasi, Massimiliano; Turri, Enrico; Atria, Jose Joaquin; Christensen, Heidi; Marxer, Ricard; Desideri, Lorenzo; Coy, Andre; Tamburini, Fabio; Green, Phil

2017-01-01

A better use of the increasing functional capabilities of home automation systems and Internet of Things (IoT) devices to support the needs of users with disability, is the subject of a research project currently conducted by Area Ausili (Assistive Technology Area), a department of Polo Tecnologico Regionale Corte Roncati of the Local Health Trust of Bologna (Italy), in collaboration with AIAS Ausilioteca Assistive Technology (AT) Team. The main aim of the project is to develop experimental low cost systems for environmental control through simplified and accessible user interfaces. Many of the activities are focused on automatic speech recognition and are developed in the framework of the CloudCAST project. In this paper we report on the first technical achievements of the project and discuss future possible developments and applications within and outside CloudCAST.

Biologically-Inspired Spike-Based Automatic Speech Recognition of Isolated Digits Over a Reproducing Kernel Hilbert Space

PubMed Central

Li, Kan; Príncipe, José C.

2018-01-01

This paper presents a novel real-time dynamic framework for quantifying time-series structure in spoken words using spikes. Audio signals are converted into multi-channel spike trains using a biologically-inspired leaky integrate-and-fire (LIF) spike generator. These spike trains are mapped into a function space of infinite dimension, i.e., a Reproducing Kernel Hilbert Space (RKHS) using point-process kernels, where a state-space model learns the dynamics of the multidimensional spike input using gradient descent learning. This kernelized recurrent system is very parsimonious and achieves the necessary memory depth via feedback of its internal states when trained discriminatively, utilizing the full context of the phoneme sequence. A main advantage of modeling nonlinear dynamics using state-space trajectories in the RKHS is that it imposes no restriction on the relationship between the exogenous input and its internal state. We are free to choose the input representation with an appropriate kernel, and changing the kernel does not impact the system nor the learning algorithm. Moreover, we show that this novel framework can outperform both traditional hidden Markov model (HMM) speech processing as well as neuromorphic implementations based on spiking neural network (SNN), yielding accurate and ultra-low power word spotters. As a proof of concept, we demonstrate its capabilities using the benchmark TI-46 digit corpus for isolated-word automatic speech recognition (ASR) or keyword spotting. Compared to HMM using Mel-frequency cepstral coefficient (MFCC) front-end without time-derivatives, our MFCC-KAARMA offered improved performance. For spike-train front-end, spike-KAARMA also outperformed state-of-the-art SNN solutions. Furthermore, compared to MFCCs, spike trains provided enhanced noise robustness in certain low signal-to-noise ratio (SNR) regime. PMID:29666568

Biologically-Inspired Spike-Based Automatic Speech Recognition of Isolated Digits Over a Reproducing Kernel Hilbert Space.

PubMed

Li, Kan; Príncipe, José C

2018-01-01

This paper presents a novel real-time dynamic framework for quantifying time-series structure in spoken words using spikes. Audio signals are converted into multi-channel spike trains using a biologically-inspired leaky integrate-and-fire (LIF) spike generator. These spike trains are mapped into a function space of infinite dimension, i.e., a Reproducing Kernel Hilbert Space (RKHS) using point-process kernels, where a state-space model learns the dynamics of the multidimensional spike input using gradient descent learning. This kernelized recurrent system is very parsimonious and achieves the necessary memory depth via feedback of its internal states when trained discriminatively, utilizing the full context of the phoneme sequence. A main advantage of modeling nonlinear dynamics using state-space trajectories in the RKHS is that it imposes no restriction on the relationship between the exogenous input and its internal state. We are free to choose the input representation with an appropriate kernel, and changing the kernel does not impact the system nor the learning algorithm. Moreover, we show that this novel framework can outperform both traditional hidden Markov model (HMM) speech processing as well as neuromorphic implementations based on spiking neural network (SNN), yielding accurate and ultra-low power word spotters. As a proof of concept, we demonstrate its capabilities using the benchmark TI-46 digit corpus for isolated-word automatic speech recognition (ASR) or keyword spotting. Compared to HMM using Mel-frequency cepstral coefficient (MFCC) front-end without time-derivatives, our MFCC-KAARMA offered improved performance. For spike-train front-end, spike-KAARMA also outperformed state-of-the-art SNN solutions. Furthermore, compared to MFCCs, spike trains provided enhanced noise robustness in certain low signal-to-noise ratio (SNR) regime.

Speech intelligibility enhancement after maxillary denture treatment and its impact on quality of life.

PubMed

Knipfer, Christian; Riemann, Max; Bocklet, Tobias; Noeth, Elmar; Schuster, Maria; Sokol, Biljana; Eitner, Stephan; Nkenke, Emeka; Stelzle, Florian

2014-01-01

Tooth loss and its prosthetic rehabilitation significantly affect speech intelligibility. However, little is known about the influence of speech deficiencies on oral health-related quality of life (OHRQoL). The aim of this study was to investigate whether speech intelligibility enhancement through prosthetic rehabilitation significantly influences OHRQoL in patients wearing complete maxillary dentures. Speech intelligibility by means of an automatic speech recognition system (ASR) was prospectively evaluated and compared with subjectively assessed Oral Health Impact Profile (OHIP) scores. Speech was recorded in 28 edentulous patients 1 week prior to the fabrication of new complete maxillary dentures and 6 months thereafter. Speech intelligibility was computed based on the word accuracy (WA) by means of an ASR and compared with a matched control group. One week before and 6 months after rehabilitation, patients assessed themselves for OHRQoL. Speech intelligibility improved significantly after 6 months. Subjects reported a significantly higher OHRQoL after maxillary rehabilitation with complete dentures. No significant correlation was found between the OHIP sum score or its subscales to the WA. Speech intelligibility enhancement achieved through the fabrication of new complete maxillary dentures might not be in the forefront of the patients' perception of their quality of life. For the improvement of OHRQoL in patients wearing complete maxillary dentures, food intake and mastication as well as freedom from pain play a more prominent role.

Speech endpoint detection with non-language speech sounds for generic speech processing applications

NASA Astrophysics Data System (ADS)

McClain, Matthew; Romanowski, Brian

2009-05-01

Non-language speech sounds (NLSS) are sounds produced by humans that do not carry linguistic information. Examples of these sounds are coughs, clicks, breaths, and filled pauses such as "uh" and "um" in English. NLSS are prominent in conversational speech, but can be a significant source of errors in speech processing applications. Traditionally, these sounds are ignored by speech endpoint detection algorithms, where speech regions are identified in the audio signal prior to processing. The ability to filter NLSS as a pre-processing step can significantly enhance the performance of many speech processing applications, such as speaker identification, language identification, and automatic speech recognition. In order to be used in all such applications, NLSS detection must be performed without the use of language models that provide knowledge of the phonology and lexical structure of speech. This is especially relevant to situations where the languages used in the audio are not known apriori. We present the results of preliminary experiments using data from American and British English speakers, in which segments of audio are classified as language speech sounds (LSS) or NLSS using a set of acoustic features designed for language-agnostic NLSS detection and a hidden-Markov model (HMM) to model speech generation. The results of these experiments indicate that the features and model used are capable of detection certain types of NLSS, such as breaths and clicks, while detection of other types of NLSS such as filled pauses will require future research.

When speaker identity is unavoidable: Neural processing of speaker identity cues in natural speech.

PubMed

Tuninetti, Alba; Chládková, Kateřina; Peter, Varghese; Schiller, Niels O; Escudero, Paola

2017-11-01

Speech sound acoustic properties vary largely across speakers and accents. When perceiving speech, adult listeners normally disregard non-linguistic variation caused by speaker or accent differences, in order to comprehend the linguistic message, e.g. to correctly identify a speech sound or a word. Here we tested whether the process of normalizing speaker and accent differences, facilitating the recognition of linguistic information, is found at the level of neural processing, and whether it is modulated by the listeners' native language. In a multi-deviant oddball paradigm, native and nonnative speakers of Dutch were exposed to naturally-produced Dutch vowels varying in speaker, sex, accent, and phoneme identity. Unexpectedly, the analysis of mismatch negativity (MMN) amplitudes elicited by each type of change shows a large degree of early perceptual sensitivity to non-linguistic cues. This finding on perception of naturally-produced stimuli contrasts with previous studies examining the perception of synthetic stimuli wherein adult listeners automatically disregard acoustic cues to speaker identity. The present finding bears relevance to speech normalization theories, suggesting that at an unattended level of processing, listeners are indeed sensitive to changes in fundamental frequency in natural speech tokens. Copyright © 2017 Elsevier Inc. All rights reserved.

Intelligibility Evaluation of Pathological Speech through Multigranularity Feature Extraction and Optimization.

PubMed

Fang, Chunying; Li, Haifeng; Ma, Lin; Zhang, Mancai

2017-01-01

Pathological speech usually refers to speech distortion resulting from illness or other biological insults. The assessment of pathological speech plays an important role in assisting the experts, while automatic evaluation of speech intelligibility is difficult because it is usually nonstationary and mutational. In this paper, we carry out an independent innovation of feature extraction and reduction, and we describe a multigranularity combined feature scheme which is optimized by the hierarchical visual method. A novel method of generating feature set based on S -transform and chaotic analysis is proposed. There are BAFS (430, basic acoustics feature), local spectral characteristics MSCC (84, Mel S -transform cepstrum coefficients), and chaotic features (12). Finally, radar chart and F -score are proposed to optimize the features by the hierarchical visual fusion. The feature set could be optimized from 526 to 96 dimensions based on NKI-CCRT corpus and 104 dimensions based on SVD corpus. The experimental results denote that new features by support vector machine (SVM) have the best performance, with a recognition rate of 84.4% on NKI-CCRT corpus and 78.7% on SVD corpus. The proposed method is thus approved to be effective and reliable for pathological speech intelligibility evaluation.

The Effect of Dynamic Pitch on Speech Recognition in Temporally Modulated Noise.

PubMed

Shen, Jing; Souza, Pamela E

2017-09-18

This study investigated the effect of dynamic pitch in target speech on older and younger listeners' speech recognition in temporally modulated noise. First, we examined whether the benefit from dynamic-pitch cues depends on the temporal modulation of noise. Second, we tested whether older listeners can benefit from dynamic-pitch cues for speech recognition in noise. Last, we explored the individual factors that predict the amount of dynamic-pitch benefit for speech recognition in noise. Younger listeners with normal hearing and older listeners with varying levels of hearing sensitivity participated in the study, in which speech reception thresholds were measured with sentences in nonspeech noise. The younger listeners benefited more from dynamic pitch for speech recognition in temporally modulated noise than unmodulated noise. Older listeners were able to benefit from the dynamic-pitch cues but received less benefit from noise modulation than the younger listeners. For those older listeners with hearing loss, the amount of hearing loss strongly predicted the dynamic-pitch benefit for speech recognition in noise. Dynamic-pitch cues aid speech recognition in noise, particularly when noise has temporal modulation. Hearing loss negatively affects the dynamic-pitch benefit to older listeners with significant hearing loss.

The Effect of Dynamic Pitch on Speech Recognition in Temporally Modulated Noise

PubMed Central

Souza, Pamela E.

2017-01-01

Purpose This study investigated the effect of dynamic pitch in target speech on older and younger listeners' speech recognition in temporally modulated noise. First, we examined whether the benefit from dynamic-pitch cues depends on the temporal modulation of noise. Second, we tested whether older listeners can benefit from dynamic-pitch cues for speech recognition in noise. Last, we explored the individual factors that predict the amount of dynamic-pitch benefit for speech recognition in noise. Method Younger listeners with normal hearing and older listeners with varying levels of hearing sensitivity participated in the study, in which speech reception thresholds were measured with sentences in nonspeech noise. Results The younger listeners benefited more from dynamic pitch for speech recognition in temporally modulated noise than unmodulated noise. Older listeners were able to benefit from the dynamic-pitch cues but received less benefit from noise modulation than the younger listeners. For those older listeners with hearing loss, the amount of hearing loss strongly predicted the dynamic-pitch benefit for speech recognition in noise. Conclusions Dynamic-pitch cues aid speech recognition in noise, particularly when noise has temporal modulation. Hearing loss negatively affects the dynamic-pitch benefit to older listeners with significant hearing loss. PMID:28800370

Machine learning based sample extraction for automatic speech recognition using dialectal Assamese speech.

PubMed

Agarwalla, Swapna; Sarma, Kandarpa Kumar

2016-06-01

Automatic Speaker Recognition (ASR) and related issues are continuously evolving as inseparable elements of Human Computer Interaction (HCI). With assimilation of emerging concepts like big data and Internet of Things (IoT) as extended elements of HCI, ASR techniques are found to be passing through a paradigm shift. Oflate, learning based techniques have started to receive greater attention from research communities related to ASR owing to the fact that former possess natural ability to mimic biological behavior and that way aids ASR modeling and processing. The current learning based ASR techniques are found to be evolving further with incorporation of big data, IoT like concepts. Here, in this paper, we report certain approaches based on machine learning (ML) used for extraction of relevant samples from big data space and apply them for ASR using certain soft computing techniques for Assamese speech with dialectal variations. A class of ML techniques comprising of the basic Artificial Neural Network (ANN) in feedforward (FF) and Deep Neural Network (DNN) forms using raw speech, extracted features and frequency domain forms are considered. The Multi Layer Perceptron (MLP) is configured with inputs in several forms to learn class information obtained using clustering and manual labeling. DNNs are also used to extract specific sentence types. Initially, from a large storage, relevant samples are selected and assimilated. Next, a few conventional methods are used for feature extraction of a few selected types. The features comprise of both spectral and prosodic types. These are applied to Recurrent Neural Network (RNN) and Fully Focused Time Delay Neural Network (FFTDNN) structures to evaluate their performance in recognizing mood, dialect, speaker and gender variations in dialectal Assamese speech. The system is tested under several background noise conditions by considering the recognition rates (obtained using confusion matrices and manually) and computation time. It is found that the proposed ML based sentence extraction techniques and the composite feature set used with RNN as classifier outperform all other approaches. By using ANN in FF form as feature extractor, the performance of the system is evaluated and a comparison is made. Experimental results show that the application of big data samples has enhanced the learning of the ASR system. Further, the ANN based sample and feature extraction techniques are found to be efficient enough to enable application of ML techniques in big data aspects as part of ASR systems. Copyright © 2015 Elsevier Ltd. All rights reserved.

Task-dependent modulation of the visual sensory thalamus assists visual-speech recognition.

PubMed

Díaz, Begoña; Blank, Helen; von Kriegstein, Katharina

2018-05-14

The cerebral cortex modulates early sensory processing via feed-back connections to sensory pathway nuclei. The functions of this top-down modulation for human behavior are poorly understood. Here, we show that top-down modulation of the visual sensory thalamus (the lateral geniculate body, LGN) is involved in visual-speech recognition. In two independent functional magnetic resonance imaging (fMRI) studies, LGN response increased when participants processed fast-varying features of articulatory movements required for visual-speech recognition, as compared to temporally more stable features required for face identification with the same stimulus material. The LGN response during the visual-speech task correlated positively with the visual-speech recognition scores across participants. In addition, the task-dependent modulation was present for speech movements and did not occur for control conditions involving non-speech biological movements. In face-to-face communication, visual speech recognition is used to enhance or even enable understanding what is said. Speech recognition is commonly explained in frameworks focusing on cerebral cortex areas. Our findings suggest that task-dependent modulation at subcortical sensory stages has an important role for communication: Together with similar findings in the auditory modality the findings imply that task-dependent modulation of the sensory thalami is a general mechanism to optimize speech recognition. Copyright © 2018. Published by Elsevier Inc.

Syntactic error modeling and scoring normalization in speech recognition: Error modeling and scoring normalization in the speech recognition task for adult literacy training

NASA Technical Reports Server (NTRS)

Olorenshaw, Lex; Trawick, David

1991-01-01

The purpose was to develop a speech recognition system to be able to detect speech which is pronounced incorrectly, given that the text of the spoken speech is known to the recognizer. Better mechanisms are provided for using speech recognition in a literacy tutor application. Using a combination of scoring normalization techniques and cheater-mode decoding, a reasonable acceptance/rejection threshold was provided. In continuous speech, the system was tested to be able to provide above 80 pct. correct acceptance of words, while correctly rejecting over 80 pct. of incorrectly pronounced words.

Increase in Speech Recognition due to Linguistic Mismatch Between Target and Masker Speech: Monolingual and Simultaneous Bilingual Performance

PubMed Central

Calandruccio, Lauren; Zhou, Haibo

2014-01-01

Purpose To examine whether improved speech recognition during linguistically mismatched target–masker experiments is due to linguistic unfamiliarity of the masker speech or linguistic dissimilarity between the target and masker speech. Method Monolingual English speakers (n = 20) and English–Greek simultaneous bilinguals (n = 20) listened to English sentences in the presence of competing English and Greek speech. Data were analyzed using mixed-effects regression models to determine differences in English recogition performance between the 2 groups and 2 masker conditions. Results Results indicated that English sentence recognition for monolinguals and simultaneous English–Greek bilinguals improved when the masker speech changed from competing English to competing Greek speech. Conclusion The improvement in speech recognition that has been observed for linguistically mismatched target–masker experiments cannot be simply explained by the masker language being linguistically unknown or unfamiliar to the listeners. Listeners can improve their speech recognition in linguistically mismatched target–masker experiments even when the listener is able to obtain meaningful linguistic information from the masker speech. PMID:24167230

[Advantages and Application Prospects of Deep Learning in Image Recognition and Bone Age Assessment].

PubMed

Hu, T H; Wan, L; Liu, T A; Wang, M W; Chen, T; Wang, Y H

2017-12-01

Deep learning and neural network models have been new research directions and hot issues in the fields of machine learning and artificial intelligence in recent years. Deep learning has made a breakthrough in the applications of image and speech recognitions, and also has been extensively used in the fields of face recognition and information retrieval because of its special superiority. Bone X-ray images express different variations in black-white-gray gradations, which have image features of black and white contrasts and level differences. Based on these advantages of deep learning in image recognition, we combine it with the research of bone age assessment to provide basic datum for constructing a forensic automatic system of bone age assessment. This paper reviews the basic concept and network architectures of deep learning, and describes its recent research progress on image recognition in different research fields at home and abroad, and explores its advantages and application prospects in bone age assessment. Copyright© by the Editorial Department of Journal of Forensic Medicine.

The Effect of Lexical Content on Dichotic Speech Recognition in Older Adults.

PubMed

Findlen, Ursula M; Roup, Christina M

2016-01-01

Age-related auditory processing deficits have been shown to negatively affect speech recognition for older adult listeners. In contrast, older adults gain benefit from their ability to make use of semantic and lexical content of the speech signal (i.e., top-down processing), particularly in complex listening situations. Assessment of auditory processing abilities among aging adults should take into consideration semantic and lexical content of the speech signal. The purpose of this study was to examine the effects of lexical and attentional factors on dichotic speech recognition performance characteristics for older adult listeners. A repeated measures design was used to examine differences in dichotic word recognition as a function of lexical and attentional factors. Thirty-five older adults (61-85 yr) with sensorineural hearing loss participated in this study. Dichotic speech recognition was evaluated using consonant-vowel-consonant (CVC) word and nonsense CVC syllable stimuli administered in the free recall, directed recall right, and directed recall left response conditions. Dichotic speech recognition performance for nonsense CVC syllables was significantly poorer than performance for CVC words. Dichotic recognition performance varied across response condition for both stimulus types, which is consistent with previous studies on dichotic speech recognition. Inspection of individual results revealed that five listeners demonstrated an auditory-based left ear deficit for one or both stimulus types. Lexical content of stimulus materials affects performance characteristics for dichotic speech recognition tasks in the older adult population. The use of nonsense CVC syllable material may provide a way to assess dichotic speech recognition performance while potentially lessening the effects of lexical content on performance (i.e., measuring bottom-up auditory function both with and without top-down processing). American Academy of Audiology.

Use of speech-to-text technology for documentation by healthcare providers.

PubMed

Ajami, Sima

2016-01-01

Medical records are a critical component of a patient's treatment. However, documentation of patient-related information is considered a secondary activity in the provision of healthcare services, often leading to incomplete medical records and patient data of low quality. Advances in information technology (IT) in the health system and registration of information in electronic health records (EHR) using speechto- text conversion software have facilitated service delivery. This narrative review is a literature search with the help of libraries, books, conference proceedings, databases of Science Direct, PubMed, Proquest, Springer, SID (Scientific Information Database), and search engines such as Yahoo, and Google. I used the following keywords and their combinations: speech recognition, automatic report documentation, voice to text software, healthcare, information, and voice recognition. Due to lack of knowledge of other languages, I searched all texts in English or Persian with no time limits. Of a total of 70, only 42 articles were selected. Speech-to-text conversion technology offers opportunities to improve the documentation process of medical records, reduce cost and time of recording information, enhance the quality of documentation, improve the quality of services provided to patients, and support healthcare providers in legal matters. Healthcare providers should recognize the impact of this technology on service delivery.

Improving on hidden Markov models: An articulatorily constrained, maximum likelihood approach to speech recognition and speech coding

DOE Office of Scientific and Technical Information (OSTI.GOV)

Hogden, J.

The goal of the proposed research is to test a statistical model of speech recognition that incorporates the knowledge that speech is produced by relatively slow motions of the tongue, lips, and other speech articulators. This model is called Maximum Likelihood Continuity Mapping (Malcom). Many speech researchers believe that by using constraints imposed by articulator motions, we can improve or replace the current hidden Markov model based speech recognition algorithms. Unfortunately, previous efforts to incorporate information about articulation into speech recognition algorithms have suffered because (1) slight inaccuracies in our knowledge or the formulation of our knowledge about articulation maymore » decrease recognition performance, (2) small changes in the assumptions underlying models of speech production can lead to large changes in the speech derived from the models, and (3) collecting measurements of human articulator positions in sufficient quantity for training a speech recognition algorithm is still impractical. The most interesting (and in fact, unique) quality of Malcom is that, even though Malcom makes use of a mapping between acoustics and articulation, Malcom can be trained to recognize speech using only acoustic data. By learning the mapping between acoustics and articulation using only acoustic data, Malcom avoids the difficulties involved in collecting articulator position measurements and does not require an articulatory synthesizer model to estimate the mapping between vocal tract shapes and speech acoustics. Preliminary experiments that demonstrate that Malcom can learn the mapping between acoustics and articulation are discussed. Potential applications of Malcom aside from speech recognition are also discussed. Finally, specific deliverables resulting from the proposed research are described.« less

An articulatorily constrained, maximum entropy approach to speech recognition and speech coding

DOE Office of Scientific and Technical Information (OSTI.GOV)

Hogden, J.

Hidden Markov models (HMM`s) are among the most popular tools for performing computer speech recognition. One of the primary reasons that HMM`s typically outperform other speech recognition techniques is that the parameters used for recognition are determined by the data, not by preconceived notions of what the parameters should be. This makes HMM`s better able to deal with intra- and inter-speaker variability despite the limited knowledge of how speech signals vary and despite the often limited ability to correctly formulate rules describing variability and invariance in speech. In fact, it is often the case that when HMM parameter values aremore » constrained using the limited knowledge of speech, recognition performance decreases. However, the structure of an HMM has little in common with the mechanisms underlying speech production. Here, the author argues that by using probabilistic models that more accurately embody the process of speech production, he can create models that have all the advantages of HMM`s, but that should more accurately capture the statistical properties of real speech samples--presumably leading to more accurate speech recognition. The model he will discuss uses the fact that speech articulators move smoothly and continuously. Before discussing how to use articulatory constraints, he will give a brief description of HMM`s. This will allow him to highlight the similarities and differences between HMM`s and the proposed technique.« less

Evaluation of Adaptive Noise Management Technologies for School-Age Children with Hearing Loss.

PubMed

Wolfe, Jace; Duke, Mila; Schafer, Erin; Jones, Christine; Rakita, Lori

2017-05-01

Children with hearing loss experience significant difficulty understanding speech in noisy and reverberant situations. Adaptive noise management technologies, such as fully adaptive directional microphones and digital noise reduction, have the potential to improve communication in noise for children with hearing aids. However, there are no published studies evaluating the potential benefits children receive from the use of adaptive noise management technologies in simulated real-world environments as well as in daily situations. The objective of this study was to compare speech recognition, speech intelligibility ratings (SIRs), and sound preferences of children using hearing aids equipped with and without adaptive noise management technologies. A single-group, repeated measures design was used to evaluate performance differences obtained in four simulated environments. In each simulated environment, participants were tested in a basic listening program with minimal noise management features, a manual program designed for that scene, and the hearing instruments' adaptive operating system that steered hearing instrument parameterization based on the characteristics of the environment. Twelve children with mild to moderately severe sensorineural hearing loss. Speech recognition and SIRs were evaluated in three hearing aid programs with and without noise management technologies across two different test sessions and various listening environments. Also, the participants' perceptual hearing performance in daily real-world listening situations with two of the hearing aid programs was evaluated during a four- to six-week field trial that took place between the two laboratory sessions. On average, the use of adaptive noise management technology improved sentence recognition in noise for speech presented in front of the participant but resulted in a decrement in performance for signals arriving from behind when the participant was facing forward. However, the improvement with adaptive noise management exceeded the decrement obtained when the signal arrived from behind. Most participants reported better subjective SIRs when using adaptive noise management technologies, particularly when the signal of interest arrived from in front of the listener. In addition, most participants reported a preference for the technology with an automatically switching, adaptive directional microphone and adaptive noise reduction in real-world listening situations when compared to conventional, omnidirectional microphone use with minimal noise reduction processing. Use of the adaptive noise management technologies evaluated in this study improves school-age children's speech recognition in noise for signals arriving from the front. Although a small decrement in speech recognition in noise was observed for signals arriving from behind the listener, most participants reported a preference for use of noise management technology both when the signal arrived from in front and from behind the child. The results of this study suggest that adaptive noise management technologies should be considered for use with school-age children when listening in academic and social situations. American Academy of Audiology

Is Listening in Noise Worth It? The Neurobiology of Speech Recognition in Challenging Listening Conditions.

PubMed

Eckert, Mark A; Teubner-Rhodes, Susan; Vaden, Kenneth I

2016-01-01

This review examines findings from functional neuroimaging studies of speech recognition in noise to provide a neural systems level explanation for the effort and fatigue that can be experienced during speech recognition in challenging listening conditions. Neuroimaging studies of speech recognition consistently demonstrate that challenging listening conditions engage neural systems that are used to monitor and optimize performance across a wide range of tasks. These systems appear to improve speech recognition in younger and older adults, but sustained engagement of these systems also appears to produce an experience of effort and fatigue that may affect the value of communication. When considered in the broader context of the neuroimaging and decision making literature, the speech recognition findings from functional imaging studies indicate that the expected value, or expected level of speech recognition given the difficulty of listening conditions, should be considered when measuring effort and fatigue. The authors propose that the behavioral economics or neuroeconomics of listening can provide a conceptual and experimental framework for understanding effort and fatigue that may have clinical significance.

Is Listening in Noise Worth It? The Neurobiology of Speech Recognition in Challenging Listening Conditions

PubMed Central

Eckert, Mark A.; Teubner-Rhodes, Susan; Vaden, Kenneth I.

2016-01-01

This review examines findings from functional neuroimaging studies of speech recognition in noise to provide a neural systems level explanation for the effort and fatigue that can be experienced during speech recognition in challenging listening conditions. Neuroimaging studies of speech recognition consistently demonstrate that challenging listening conditions engage neural systems that are used to monitor and optimize performance across a wide range of tasks. These systems appear to improve speech recognition in younger and older adults, but sustained engagement of these systems also appears to produce an experience of effort and fatigue that may affect the value of communication. When considered in the broader context of the neuroimaging and decision making literature, the speech recognition findings from functional imaging studies indicate that the expected value, or expected level of speech recognition given the difficulty of listening conditions, should be considered when measuring effort and fatigue. We propose that the behavioral economics and/or neuroeconomics of listening can provide a conceptual and experimental framework for understanding effort and fatigue that may have clinical significance. PMID:27355759

Speech Recognition and Parent Ratings From Auditory Development Questionnaires in Children Who Are Hard of Hearing.

PubMed

McCreery, Ryan W; Walker, Elizabeth A; Spratford, Meredith; Oleson, Jacob; Bentler, Ruth; Holte, Lenore; Roush, Patricia

2015-01-01

Progress has been made in recent years in the provision of amplification and early intervention for children who are hard of hearing. However, children who use hearing aids (HAs) may have inconsistent access to their auditory environment due to limitations in speech audibility through their HAs or limited HA use. The effects of variability in children's auditory experience on parent-reported auditory skills questionnaires and on speech recognition in quiet and in noise were examined for a large group of children who were followed as part of the Outcomes of Children with Hearing Loss study. Parent ratings on auditory development questionnaires and children's speech recognition were assessed for 306 children who are hard of hearing. Children ranged in age from 12 months to 9 years. Three questionnaires involving parent ratings of auditory skill development and behavior were used, including the LittlEARS Auditory Questionnaire, Parents Evaluation of Oral/Aural Performance in Children rating scale, and an adaptation of the Speech, Spatial, and Qualities of Hearing scale. Speech recognition in quiet was assessed using the Open- and Closed-Set Test, Early Speech Perception test, Lexical Neighborhood Test, and Phonetically Balanced Kindergarten word lists. Speech recognition in noise was assessed using the Computer-Assisted Speech Perception Assessment. Children who are hard of hearing were compared with peers with normal hearing matched for age, maternal educational level, and nonverbal intelligence. The effects of aided audibility, HA use, and language ability on parent responses to auditory development questionnaires and on children's speech recognition were also examined. Children who are hard of hearing had poorer performance than peers with normal hearing on parent ratings of auditory skills and had poorer speech recognition. Significant individual variability among children who are hard of hearing was observed. Children with greater aided audibility through their HAs, more hours of HA use, and better language abilities generally had higher parent ratings of auditory skills and better speech-recognition abilities in quiet and in noise than peers with less audibility, more limited HA use, or poorer language abilities. In addition to the auditory and language factors that were predictive for speech recognition in quiet, phonological working memory was also a positive predictor for word recognition abilities in noise. Children who are hard of hearing continue to experience delays in auditory skill development and speech-recognition abilities compared with peers with normal hearing. However, significant improvements in these domains have occurred in comparison to similar data reported before the adoption of universal newborn hearing screening and early intervention programs for children who are hard of hearing. Increasing the audibility of speech has a direct positive effect on auditory skill development and speech-recognition abilities and also may enhance these skills by improving language abilities in children who are hard of hearing. Greater number of hours of HA use also had a significant positive impact on parent ratings of auditory skills and children's speech recognition.

A hardware experimental platform for neural circuits in the auditory cortex

NASA Astrophysics Data System (ADS)

Rodellar-Biarge, Victoria; García-Dominguez, Pablo; Ruiz-Rizaldos, Yago; Gómez-Vilda, Pedro

2011-05-01

Speech processing in the human brain is a very complex process far from being fully understood although much progress has been done recently. Neuromorphic Speech Processing is a new research orientation in bio-inspired systems approach to find solutions to automatic treatment of specific problems (recognition, synthesis, segmentation, diarization, etc) which can not be adequately solved using classical algorithms. In this paper a neuromorphic speech processing architecture is presented. The systematic bottom-up synthesis of layered structures reproduce the dynamic feature detection of speech related to plausible neural circuits which work as interpretation centres located in the Auditory Cortex. The elementary model is based on Hebbian neuron-like units. For the computation of the architecture a flexible framework is proposed in the environment of Matlab®/Simulink®/HDL, which allows building models in different description styles, complexity and implementation levels. It provides a flexible platform for experimenting on the influence of the number of neurons and interconnections, in the precision of the results and in performance evaluation. The experimentation with different architecture configurations may help both in better understanding how neural circuits may work in the brain as well as in how speech processing can benefit from this understanding.

Speech Recognition as a Transcription Aid: A Randomized Comparison With Standard Transcription

PubMed Central

Mohr, David N.; Turner, David W.; Pond, Gregory R.; Kamath, Joseph S.; De Vos, Cathy B.; Carpenter, Paul C.

2003-01-01

Objective. Speech recognition promises to reduce information entry costs for clinical information systems. It is most likely to be accepted across an organization if physicians can dictate without concerning themselves with real-time recognition and editing; assistants can then edit and process the computer-generated document. Our objective was to evaluate the use of speech-recognition technology in a randomized controlled trial using our institutional infrastructure. Design. Clinical note dictations from physicians in two specialty divisions were randomized to either a standard transcription process or a speech-recognition process. Secretaries and transcriptionists also were assigned randomly to each of these processes. Measurements. The duration of each dictation was measured. The amount of time spent processing a dictation to yield a finished document also was measured. Secretarial and transcriptionist productivity, defined as hours of secretary work per minute of dictation processed, was determined for speech recognition and standard transcription. Results. Secretaries in the endocrinology division were 87.3% (confidence interval, 83.3%, 92.3%) as productive with the speech-recognition technology as implemented in this study as they were using standard transcription. Psychiatry transcriptionists and secretaries were similarly less productive. Author, secretary, and type of clinical note were significant (p < 0.05) predictors of productivity. Conclusion. When implemented in an organization with an existing document-processing infrastructure (which included training and interfaces of the speech-recognition editor with the existing document entry application), speech recognition did not improve the productivity of secretaries or transcriptionists. PMID:12509359

Advances in audio source seperation and multisource audio content retrieval

NASA Astrophysics Data System (ADS)

Vincent, Emmanuel

2012-06-01

Audio source separation aims to extract the signals of individual sound sources from a given recording. In this paper, we review three recent advances which improve the robustness of source separation in real-world challenging scenarios and enable its use for multisource content retrieval tasks, such as automatic speech recognition (ASR) or acoustic event detection (AED) in noisy environments. We present a Flexible Audio Source Separation Toolkit (FASST) and discuss its advantages compared to earlier approaches such as independent component analysis (ICA) and sparse component analysis (SCA). We explain how cues as diverse as harmonicity, spectral envelope, temporal fine structure or spatial location can be jointly exploited by this toolkit. We subsequently present the uncertainty decoding (UD) framework for the integration of audio source separation and audio content retrieval. We show how the uncertainty about the separated source signals can be accurately estimated and propagated to the features. Finally, we explain how this uncertainty can be efficiently exploited by a classifier, both at the training and the decoding stage. We illustrate the resulting performance improvements in terms of speech separation quality and speaker recognition accuracy.

Speech emotion recognition methods: A literature review

NASA Astrophysics Data System (ADS)

Basharirad, Babak; Moradhaseli, Mohammadreza

2017-10-01

Recently, attention of the emotional speech signals research has been boosted in human machine interfaces due to availability of high computation capability. There are many systems proposed in the literature to identify the emotional state through speech. Selection of suitable feature sets, design of a proper classifications methods and prepare an appropriate dataset are the main key issues of speech emotion recognition systems. This paper critically analyzed the current available approaches of speech emotion recognition methods based on the three evaluating parameters (feature set, classification of features, accurately usage). In addition, this paper also evaluates the performance and limitations of available methods. Furthermore, it highlights the current promising direction for improvement of speech emotion recognition systems.

Neuroscience-inspired computational systems for speech recognition under noisy conditions

NASA Astrophysics Data System (ADS)

Schafer, Phillip B.

Humans routinely recognize speech in challenging acoustic environments with background music, engine sounds, competing talkers, and other acoustic noise. However, today's automatic speech recognition (ASR) systems perform poorly in such environments. In this dissertation, I present novel methods for ASR designed to approach human-level performance by emulating the brain's processing of sounds. I exploit recent advances in auditory neuroscience to compute neuron-based representations of speech, and design novel methods for decoding these representations to produce word transcriptions. I begin by considering speech representations modeled on the spectrotemporal receptive fields of auditory neurons. These representations can be tuned to optimize a variety of objective functions, which characterize the response properties of a neural population. I propose an objective function that explicitly optimizes the noise invariance of the neural responses, and find that it gives improved performance on an ASR task in noise compared to other objectives. The method as a whole, however, fails to significantly close the performance gap with humans. I next consider speech representations that make use of spiking model neurons. The neurons in this method are feature detectors that selectively respond to spectrotemporal patterns within short time windows in speech. I consider a number of methods for training the response properties of the neurons. In particular, I present a method using linear support vector machines (SVMs) and show that this method produces spikes that are robust to additive noise. I compute the spectrotemporal receptive fields of the neurons for comparison with previous physiological results. To decode the spike-based speech representations, I propose two methods designed to work on isolated word recordings. The first method uses a classical ASR technique based on the hidden Markov model. The second method is a novel template-based recognition scheme that takes advantage of the neural representation's invariance in noise. The scheme centers on a speech similarity measure based on the longest common subsequence between spike sequences. The combined encoding and decoding scheme outperforms a benchmark system in extremely noisy acoustic conditions. Finally, I consider methods for decoding spike representations of continuous speech. To help guide the alignment of templates to words, I design a syllable detection scheme that robustly marks the locations of syllabic nuclei. The scheme combines SVM-based training with a peak selection algorithm designed to improve noise tolerance. By incorporating syllable information into the ASR system, I obtain strong recognition results in noisy conditions, although the performance in noiseless conditions is below the state of the art. The work presented here constitutes a novel approach to the problem of ASR that can be applied in the many challenging acoustic environments in which we use computer technologies today. The proposed spike-based processing methods can potentially be exploited in effcient hardware implementations and could significantly reduce the computational costs of ASR. The work also provides a framework for understanding the advantages of spike-based acoustic coding in the human brain.

Emotionally conditioning the target-speech voice enhances recognition of the target speech under "cocktail-party" listening conditions.

PubMed

Lu, Lingxi; Bao, Xiaohan; Chen, Jing; Qu, Tianshu; Wu, Xihong; Li, Liang

2018-05-01

Under a noisy "cocktail-party" listening condition with multiple people talking, listeners can use various perceptual/cognitive unmasking cues to improve recognition of the target speech against informational speech-on-speech masking. One potential unmasking cue is the emotion expressed in a speech voice, by means of certain acoustical features. However, it was unclear whether emotionally conditioning a target-speech voice that has none of the typical acoustical features of emotions (i.e., an emotionally neutral voice) can be used by listeners for enhancing target-speech recognition under speech-on-speech masking conditions. In this study we examined the recognition of target speech against a two-talker speech masker both before and after the emotionally neutral target voice was paired with a loud female screaming sound that has a marked negative emotional valence. The results showed that recognition of the target speech (especially the first keyword in a target sentence) was significantly improved by emotionally conditioning the target speaker's voice. Moreover, the emotional unmasking effect was independent of the unmasking effect of the perceived spatial separation between the target speech and the masker. Also, (skin conductance) electrodermal responses became stronger after emotional learning when the target speech and masker were perceptually co-located, suggesting an increase of listening efforts when the target speech was informationally masked. These results indicate that emotionally conditioning the target speaker's voice does not change the acoustical parameters of the target-speech stimuli, but the emotionally conditioned vocal features can be used as cues for unmasking target speech.

Automatic feedback to promote safe walking and speech loudness control in persons with multiple disabilities: two single-case studies.

PubMed

Lancioni, Giulio E; Singh, Nirbhay N; O'Reilly, Mark F; Green, Vanessa A; Alberti, Gloria; Boccasini, Adele; Smaldone, Angela; Oliva, Doretta; Bosco, Andrea

2014-08-01

Assessing automatic feedback technologies to promote safe travel and speech loudness control in two men with multiple disabilities, respectively. The men were involved in two single-case studies. In Study I, the technology involved a microprocessor, two photocells, and a verbal feedback device. The man received verbal alerting/feedback when the photocells spotted an obstacle in front of him. In Study II, the technology involved a sound-detecting unit connected to a throat and an airborne microphone, and to a vibration device. Vibration occurred when the man's speech loudness exceeded a preset level. The man included in Study I succeeded in using the automatic feedback in substitution of caregivers' alerting/feedback for safe travel. The man of Study II used the automatic feedback to successfully reduce his speech loudness. Automatic feedback can be highly effective in helping persons with multiple disabilities improve their travel and speech performance.

Integrating hidden Markov model and PRAAT: a toolbox for robust automatic speech transcription

NASA Astrophysics Data System (ADS)

Kabir, A.; Barker, J.; Giurgiu, M.

2010-09-01

An automatic time-aligned phone transcription toolbox of English speech corpora has been developed. Especially the toolbox would be very useful to generate robust automatic transcription and able to produce phone level transcription using speaker independent models as well as speaker dependent models without manual intervention. The system is based on standard Hidden Markov Models (HMM) approach and it was successfully experimented over a large audiovisual speech corpus namely GRID corpus. One of the most powerful features of the toolbox is the increased flexibility in speech processing where the speech community would be able to import the automatic transcription generated by HMM Toolkit (HTK) into a popular transcription software, PRAAT, and vice-versa. The toolbox has been evaluated through statistical analysis on GRID data which shows that automatic transcription deviates by an average of 20 ms with respect to manual transcription.

Ongoing slow oscillatory phase modulates speech intelligibility in cooperation with motor cortical activity.

PubMed

Onojima, Takayuki; Kitajo, Keiichi; Mizuhara, Hiroaki

2017-01-01

Neural oscillation is attracting attention as an underlying mechanism for speech recognition. Speech intelligibility is enhanced by the synchronization of speech rhythms and slow neural oscillation, which is typically observed as human scalp electroencephalography (EEG). In addition to the effect of neural oscillation, it has been proposed that speech recognition is enhanced by the identification of a speaker's motor signals, which are used for speech production. To verify the relationship between the effect of neural oscillation and motor cortical activity, we measured scalp EEG, and simultaneous EEG and functional magnetic resonance imaging (fMRI) during a speech recognition task in which participants were required to recognize spoken words embedded in noise sound. We proposed an index to quantitatively evaluate the EEG phase effect on behavioral performance. The results showed that the delta and theta EEG phase before speech inputs modulated the participant's response time when conducting speech recognition tasks. The simultaneous EEG-fMRI experiment showed that slow EEG activity was correlated with motor cortical activity. These results suggested that the effect of the slow oscillatory phase was associated with the activity of the motor cortex during speech recognition.

Address entry while driving: speech recognition versus a touch-screen keyboard.

PubMed

Tsimhoni, Omer; Smith, Daniel; Green, Paul

2004-01-01

A driving simulator experiment was conducted to determine the effects of entering addresses into a navigation system during driving. Participants drove on roads of varying visual demand while entering addresses. Three address entry methods were explored: word-based speech recognition, character-based speech recognition, and typing on a touch-screen keyboard. For each method, vehicle control and task measures, glance timing, and subjective ratings were examined. During driving, word-based speech recognition yielded the shortest total task time (15.3 s), followed by character-based speech recognition (41.0 s) and touch-screen keyboard (86.0 s). The standard deviation of lateral position when performing keyboard entry (0.21 m) was 60% higher than that for all other address entry methods (0.13 m). Degradation of vehicle control associated with address entry using a touch screen suggests that the use of speech recognition is favorable. Speech recognition systems with visual feedback, however, even with excellent accuracy, are not without performance consequences. Applications of this research include the design of in-vehicle navigation systems as well as other systems requiring significant driver input, such as E-mail, the Internet, and text messaging.

Performing speech recognition research with hypercard

NASA Technical Reports Server (NTRS)

Shepherd, Chip

1993-01-01

The purpose of this paper is to describe a HyperCard-based system for performing speech recognition research and to instruct Human Factors professionals on how to use the system to obtain detailed data about the user interface of a prototype speech recognition application.

Speech recognition and parent-ratings from auditory development questionnaires in children who are hard of hearing

PubMed Central

McCreery, Ryan W.; Walker, Elizabeth A.; Spratford, Meredith; Oleson, Jacob; Bentler, Ruth; Holte, Lenore; Roush, Patricia

2015-01-01

Objectives Progress has been made in recent years in the provision of amplification and early intervention for children who are hard of hearing. However, children who use hearing aids (HA) may have inconsistent access to their auditory environment due to limitations in speech audibility through their HAs or limited HA use. The effects of variability in children’s auditory experience on parent-report auditory skills questionnaires and on speech recognition in quiet and in noise were examined for a large group of children who were followed as part of the Outcomes of Children with Hearing Loss study. Design Parent ratings on auditory development questionnaires and children’s speech recognition were assessed for 306 children who are hard of hearing. Children ranged in age from 12 months to 9 years of age. Three questionnaires involving parent ratings of auditory skill development and behavior were used, including the LittlEARS Auditory Questionnaire, Parents Evaluation of Oral/Aural Performance in Children Rating Scale, and an adaptation of the Speech, Spatial and Qualities of Hearing scale. Speech recognition in quiet was assessed using the Open and Closed set task, Early Speech Perception Test, Lexical Neighborhood Test, and Phonetically-balanced Kindergarten word lists. Speech recognition in noise was assessed using the Computer-Assisted Speech Perception Assessment. Children who are hard of hearing were compared to peers with normal hearing matched for age, maternal educational level and nonverbal intelligence. The effects of aided audibility, HA use and language ability on parent responses to auditory development questionnaires and on children’s speech recognition were also examined. Results Children who are hard of hearing had poorer performance than peers with normal hearing on parent ratings of auditory skills and had poorer speech recognition. Significant individual variability among children who are hard of hearing was observed. Children with greater aided audibility through their HAs, more hours of HA use and better language abilities generally had higher parent ratings of auditory skills and better speech recognition abilities in quiet and in noise than peers with less audibility, more limited HA use or poorer language abilities. In addition to the auditory and language factors that were predictive for speech recognition in quiet, phonological working memory was also a positive predictor for word recognition abilities in noise. Conclusions Children who are hard of hearing continue to experience delays in auditory skill development and speech recognition abilities compared to peers with normal hearing. However, significant improvements in these domains have occurred in comparison to similar data reported prior to the adoption of universal newborn hearing screening and early intervention programs for children who are hard of hearing. Increasing the audibility of speech has a direct positive effect on auditory skill development and speech recognition abilities, and may also enhance these skills by improving language abilities in children who are hard of hearing. Greater number of hours of HA use also had a significant positive impact on parent ratings of auditory skills and children’s speech recognition. PMID:26731160

Automatic detection of articulation disorders in children with cleft lip and palate.

PubMed

Maier, Andreas; Hönig, Florian; Bocklet, Tobias; Nöth, Elmar; Stelzle, Florian; Nkenke, Emeka; Schuster, Maria

2009-11-01

Speech of children with cleft lip and palate (CLP) is sometimes still disordered even after adequate surgical and nonsurgical therapies. Such speech shows complex articulation disorders, which are usually assessed perceptually, consuming time and manpower. Hence, there is a need for an easy to apply and reliable automatic method. To create a reference for an automatic system, speech data of 58 children with CLP were assessed perceptually by experienced speech therapists for characteristic phonetic disorders at the phoneme level. The first part of the article aims to detect such characteristics by a semiautomatic procedure and the second to evaluate a fully automatic, thus simple, procedure. The methods are based on a combination of speech processing algorithms. The semiautomatic method achieves moderate to good agreement (kappa approximately 0.6) for the detection of all phonetic disorders. On a speaker level, significant correlations between the perceptual evaluation and the automatic system of 0.89 are obtained. The fully automatic system yields a correlation on the speaker level of 0.81 to the perceptual evaluation. This correlation is in the range of the inter-rater correlation of the listeners. The automatic speech evaluation is able to detect phonetic disorders at an experts'level without any additional human postprocessing.

Perceptual learning for speech in noise after application of binary time-frequency masks

PubMed Central

Ahmadi, Mahnaz; Gross, Vauna L.; Sinex, Donal G.

2013-01-01

Ideal time-frequency (TF) masks can reject noise and improve the recognition of speech-noise mixtures. An ideal TF mask is constructed with prior knowledge of the target speech signal. The intelligibility of a processed speech-noise mixture depends upon the threshold criterion used to define the TF mask. The study reported here assessed the effect of training on the recognition of speech in noise after processing by ideal TF masks that did not restore perfect speech intelligibility. Two groups of listeners with normal hearing listened to speech-noise mixtures processed by TF masks calculated with different threshold criteria. For each group, a threshold criterion that initially produced word recognition scores between 0.56–0.69 was chosen for training. Listeners practiced with one set of TF-masked sentences until their word recognition performance approached asymptote. Perceptual learning was quantified by comparing word-recognition scores in the first and last training sessions. Word recognition scores improved with practice for all listeners with the greatest improvement observed for the same materials used in training. PMID:23464038

The effects of reverberant self- and overlap-masking on speech recognition in cochlear implant listeners.

PubMed

Desmond, Jill M; Collins, Leslie M; Throckmorton, Chandra S

2014-06-01

Many cochlear implant (CI) listeners experience decreased speech recognition in reverberant environments [Kokkinakis et al., J. Acoust. Soc. Am. 129(5), 3221-3232 (2011)], which may be caused by a combination of self- and overlap-masking [Bolt and MacDonald, J. Acoust. Soc. Am. 21(6), 577-580 (1949)]. Determining the extent to which these effects decrease speech recognition for CI listeners may influence reverberation mitigation algorithms. This study compared speech recognition with ideal self-masking mitigation, with ideal overlap-masking mitigation, and with no mitigation. Under these conditions, mitigating either self- or overlap-masking resulted in significant improvements in speech recognition for both normal hearing subjects utilizing an acoustic model and for CI listeners using their own devices.

Children with a cochlear implant: characteristics and determinants of speech recognition, speech-recognition growth rate, and speech production.

PubMed

Wie, Ona Bø; Falkenberg, Eva-Signe; Tvete, Ole; Tomblin, Bruce

2007-05-01

The objectives of the study were to describe the characteristics of the first 79 prelingually deaf cochlear implant users in Norway and to investigate to what degree the variation in speech recognition, speech- recognition growth rate, and speech production could be explained by the characteristics of the child, the cochlear implant, the family, and the educational setting. Data gathered longitudinally were analysed using descriptive statistics, multiple regression, and growth-curve analysis. The results show that more than 50% of the variation could be explained by these characteristics. Daily user-time, non-verbal intelligence, mode of communication, length of CI experience, and educational placement had the highest effect on the outcome. The results also indicate that children educated in a bilingual approach to education have better speech perception and faster speech perception growth rate with increased focus on spoken language.

How does susceptibility to proactive interference relate to speech recognition in aided and unaided conditions?

PubMed

Ellis, Rachel J; Rönnberg, Jerker

2015-01-01

Proactive interference (PI) is the capacity to resist interference to the acquisition of new memories from information stored in the long-term memory. Previous research has shown that PI correlates significantly with the speech-in-noise recognition scores of younger adults with normal hearing. In this study, we report the results of an experiment designed to investigate the extent to which tests of visual PI relate to the speech-in-noise recognition scores of older adults with hearing loss, in aided and unaided conditions. The results suggest that measures of PI correlate significantly with speech-in-noise recognition only in the unaided condition. Furthermore the relation between PI and speech-in-noise recognition differs to that observed in younger listeners without hearing loss. The findings suggest that the relation between PI tests and the speech-in-noise recognition scores of older adults with hearing loss relates to capability of the test to index cognitive flexibility.

How does susceptibility to proactive interference relate to speech recognition in aided and unaided conditions?

PubMed Central

Ellis, Rachel J.; Rönnberg, Jerker

2015-01-01

Proactive interference (PI) is the capacity to resist interference to the acquisition of new memories from information stored in the long-term memory. Previous research has shown that PI correlates significantly with the speech-in-noise recognition scores of younger adults with normal hearing. In this study, we report the results of an experiment designed to investigate the extent to which tests of visual PI relate to the speech-in-noise recognition scores of older adults with hearing loss, in aided and unaided conditions. The results suggest that measures of PI correlate significantly with speech-in-noise recognition only in the unaided condition. Furthermore the relation between PI and speech-in-noise recognition differs to that observed in younger listeners without hearing loss. The findings suggest that the relation between PI tests and the speech-in-noise recognition scores of older adults with hearing loss relates to capability of the test to index cognitive flexibility. PMID:26283981

Visual face-movement sensitive cortex is relevant for auditory-only speech recognition.

PubMed

Riedel, Philipp; Ragert, Patrick; Schelinski, Stefanie; Kiebel, Stefan J; von Kriegstein, Katharina

2015-07-01

It is commonly assumed that the recruitment of visual areas during audition is not relevant for performing auditory tasks ('auditory-only view'). According to an alternative view, however, the recruitment of visual cortices is thought to optimize auditory-only task performance ('auditory-visual view'). This alternative view is based on functional magnetic resonance imaging (fMRI) studies. These studies have shown, for example, that even if there is only auditory input available, face-movement sensitive areas within the posterior superior temporal sulcus (pSTS) are involved in understanding what is said (auditory-only speech recognition). This is particularly the case when speakers are known audio-visually, that is, after brief voice-face learning. Here we tested whether the left pSTS involvement is causally related to performance in auditory-only speech recognition when speakers are known by face. To test this hypothesis, we applied cathodal transcranial direct current stimulation (tDCS) to the pSTS during (i) visual-only speech recognition of a speaker known only visually to participants and (ii) auditory-only speech recognition of speakers they learned by voice and face. We defined the cathode as active electrode to down-regulate cortical excitability by hyperpolarization of neurons. tDCS to the pSTS interfered with visual-only speech recognition performance compared to a control group without pSTS stimulation (tDCS to BA6/44 or sham). Critically, compared to controls, pSTS stimulation additionally decreased auditory-only speech recognition performance selectively for voice-face learned speakers. These results are important in two ways. First, they provide direct evidence that the pSTS is causally involved in visual-only speech recognition; this confirms a long-standing prediction of current face-processing models. Secondly, they show that visual face-sensitive pSTS is causally involved in optimizing auditory-only speech recognition. These results are in line with the 'auditory-visual view' of auditory speech perception, which assumes that auditory speech recognition is optimized by using predictions from previously encoded speaker-specific audio-visual internal models. Copyright © 2015 Elsevier Ltd. All rights reserved.

Distributed Fusion in Sensor Networks with Information Genealogy

DTIC Science & Technology

2011-06-28

image processing [2], acoustic and speech recognition [3], multitarget tracking [4], distributed fusion [5], and Bayesian inference [6-7]. For...Adaptation for Distant-Talking Speech Recognition." in Proc Acoustics. Speech , and Signal Processing, 2004 |4| Y Bar-Shalom and T 1-. Fortmann...used in speech recognition and other classification applications [8]. But their use in underwater mine classification is limited. In this paper, we

Prediction of consonant recognition in quiet for listeners with normal and impaired hearing using an auditory model.

PubMed

Jürgens, Tim; Ewert, Stephan D; Kollmeier, Birger; Brand, Thomas

2014-03-01

Consonant recognition was assessed in normal-hearing (NH) and hearing-impaired (HI) listeners in quiet as a function of speech level using a nonsense logatome test. Average recognition scores were analyzed and compared to recognition scores of a speech recognition model. In contrast to commonly used spectral speech recognition models operating on long-term spectra, a "microscopic" model operating in the time domain was used. Variations of the model (accounting for hearing impairment) and different model parameters (reflecting cochlear compression) were tested. Using these model variations this study examined whether speech recognition performance in quiet is affected by changes in cochlear compression, namely, a linearization, which is often observed in HI listeners. Consonant recognition scores for HI listeners were poorer than for NH listeners. The model accurately predicted the speech reception thresholds of the NH and most HI listeners. A partial linearization of the cochlear compression in the auditory model, while keeping audibility constant, produced higher recognition scores and improved the prediction accuracy. However, including listener-specific information about the exact form of the cochlear compression did not improve the prediction further.

Mispronunciation Detection for Language Learning and Speech Recognition Adaptation

ERIC Educational Resources Information Center

Ge, Zhenhao

2013-01-01

The areas of "mispronunciation detection" (or "accent detection" more specifically) within the speech recognition community are receiving increased attention now. Two application areas, namely language learning and speech recognition adaptation, are largely driving this research interest and are the focal points of this work.…

Longitudinal changes in speech recognition in older persons.

PubMed

Dubno, Judy R; Lee, Fu-Shing; Matthews, Lois J; Ahlstrom, Jayne B; Horwitz, Amy R; Mills, John H

2008-01-01

Recognition of isolated monosyllabic words in quiet and recognition of key words in low- and high-context sentences in babble were measured in a large sample of older persons enrolled in a longitudinal study of age-related hearing loss. Repeated measures were obtained yearly or every 2 to 3 years. To control for concurrent changes in pure-tone thresholds and speech levels, speech-recognition scores were adjusted using an importance-weighted speech-audibility metric (AI). Linear-regression slope estimated the rate of change in adjusted speech-recognition scores. Recognition of words in quiet declined significantly faster with age than predicted by declines in speech audibility. As subjects aged, observed scores deviated increasingly from AI-predicted scores, but this effect did not accelerate with age. Rate of decline in word recognition was significantly faster for females than males and for females with high serum progesterone levels, whereas noise history had no effect. Rate of decline did not accelerate with age but increased with degree of hearing loss, suggesting that with more severe injury to the auditory system, impairments to auditory function other than reduced audibility resulted in faster declines in word recognition as subjects aged. Recognition of key words in low- and high-context sentences in babble did not decline significantly with age.

From Birdsong to Human Speech Recognition: Bayesian Inference on a Hierarchy of Nonlinear Dynamical Systems

PubMed Central

Yildiz, Izzet B.; von Kriegstein, Katharina; Kiebel, Stefan J.

2013-01-01

Our knowledge about the computational mechanisms underlying human learning and recognition of sound sequences, especially speech, is still very limited. One difficulty in deciphering the exact means by which humans recognize speech is that there are scarce experimental findings at a neuronal, microscopic level. Here, we show that our neuronal-computational understanding of speech learning and recognition may be vastly improved by looking at an animal model, i.e., the songbird, which faces the same challenge as humans: to learn and decode complex auditory input, in an online fashion. Motivated by striking similarities between the human and songbird neural recognition systems at the macroscopic level, we assumed that the human brain uses the same computational principles at a microscopic level and translated a birdsong model into a novel human sound learning and recognition model with an emphasis on speech. We show that the resulting Bayesian model with a hierarchy of nonlinear dynamical systems can learn speech samples such as words rapidly and recognize them robustly, even in adverse conditions. In addition, we show that recognition can be performed even when words are spoken by different speakers and with different accents—an everyday situation in which current state-of-the-art speech recognition models often fail. The model can also be used to qualitatively explain behavioral data on human speech learning and derive predictions for future experiments. PMID:24068902

From birdsong to human speech recognition: bayesian inference on a hierarchy of nonlinear dynamical systems.

PubMed

Yildiz, Izzet B; von Kriegstein, Katharina; Kiebel, Stefan J

2013-01-01

Our knowledge about the computational mechanisms underlying human learning and recognition of sound sequences, especially speech, is still very limited. One difficulty in deciphering the exact means by which humans recognize speech is that there are scarce experimental findings at a neuronal, microscopic level. Here, we show that our neuronal-computational understanding of speech learning and recognition may be vastly improved by looking at an animal model, i.e., the songbird, which faces the same challenge as humans: to learn and decode complex auditory input, in an online fashion. Motivated by striking similarities between the human and songbird neural recognition systems at the macroscopic level, we assumed that the human brain uses the same computational principles at a microscopic level and translated a birdsong model into a novel human sound learning and recognition model with an emphasis on speech. We show that the resulting Bayesian model with a hierarchy of nonlinear dynamical systems can learn speech samples such as words rapidly and recognize them robustly, even in adverse conditions. In addition, we show that recognition can be performed even when words are spoken by different speakers and with different accents-an everyday situation in which current state-of-the-art speech recognition models often fail. The model can also be used to qualitatively explain behavioral data on human speech learning and derive predictions for future experiments.

Statistical assessment of speech system performance

NASA Technical Reports Server (NTRS)

Moshier, Stephen L.

1977-01-01

Methods for the normalization of performance tests results of speech recognition systems are presented. Technological accomplishments in speech recognition systems, as well as planned research activities are described.

Building Searchable Collections of Enterprise Speech Data.

ERIC Educational Resources Information Center

Cooper, James W.; Viswanathan, Mahesh; Byron, Donna; Chan, Margaret

The study has applied speech recognition and text-mining technologies to a set of recorded outbound marketing calls and analyzed the results. Since speaker-independent speech recognition technology results in a significantly lower recognition rate than that found when the recognizer is trained for a particular speaker, a number of post-processing…

Masked Speech Recognition and Reading Ability in School-Age Children: Is There a Relationship?

ERIC Educational Resources Information Center

Miller, Gabrielle; Lewis, Barbara; Benchek, Penelope; Buss, Emily; Calandruccio, Lauren

2018-01-01

Purpose: The relationship between reading (decoding) skills, phonological processing abilities, and masked speech recognition in typically developing children was explored. This experiment was designed to evaluate the relationship between phonological processing and decoding abilities and 2 aspects of masked speech recognition in typically…

Six characteristics of effective structured reporting and the inevitable integration with speech recognition.

PubMed

Liu, David; Zucherman, Mark; Tulloss, William B

2006-03-01

The reporting of radiological images is undergoing dramatic changes due to the introduction of two new technologies: structured reporting and speech recognition. Each technology has its own unique advantages. The highly organized content of structured reporting facilitates data mining and billing, whereas speech recognition offers a natural succession from the traditional dictation-transcription process. This article clarifies the distinction between the process and outcome of structured reporting, describes fundamental requirements for any effective structured reporting system, and describes the potential development of a novel, easy-to-use, customizable structured reporting system that incorporates speech recognition. This system should have all the advantages derived from structured reporting, accommodate a wide variety of user needs, and incorporate speech recognition as a natural component and extension of the overall reporting process.

Comparing auditory filter bandwidths, spectral ripple modulation detection, spectral ripple discrimination, and speech recognition: Normal and impaired hearinga)

PubMed Central

Davies-Venn, Evelyn; Nelson, Peggy; Souza, Pamela

2015-01-01

Some listeners with hearing loss show poor speech recognition scores in spite of using amplification that optimizes audibility. Beyond audibility, studies have suggested that suprathreshold abilities such as spectral and temporal processing may explain differences in amplified speech recognition scores. A variety of different methods has been used to measure spectral processing. However, the relationship between spectral processing and speech recognition is still inconclusive. This study evaluated the relationship between spectral processing and speech recognition in listeners with normal hearing and with hearing loss. Narrowband spectral resolution was assessed using auditory filter bandwidths estimated from simultaneous notched-noise masking. Broadband spectral processing was measured using the spectral ripple discrimination (SRD) task and the spectral ripple depth detection (SMD) task. Three different measures were used to assess unamplified and amplified speech recognition in quiet and noise. Stepwise multiple linear regression revealed that SMD at 2.0 cycles per octave (cpo) significantly predicted speech scores for amplified and unamplified speech in quiet and noise. Commonality analyses revealed that SMD at 2.0 cpo combined with SRD and equivalent rectangular bandwidth measures to explain most of the variance captured by the regression model. Results suggest that SMD and SRD may be promising clinical tools for diagnostic evaluation and predicting amplification outcomes. PMID:26233047

Comparing auditory filter bandwidths, spectral ripple modulation detection, spectral ripple discrimination, and speech recognition: Normal and impaired hearing.

PubMed

Davies-Venn, Evelyn; Nelson, Peggy; Souza, Pamela

2015-07-01

Some listeners with hearing loss show poor speech recognition scores in spite of using amplification that optimizes audibility. Beyond audibility, studies have suggested that suprathreshold abilities such as spectral and temporal processing may explain differences in amplified speech recognition scores. A variety of different methods has been used to measure spectral processing. However, the relationship between spectral processing and speech recognition is still inconclusive. This study evaluated the relationship between spectral processing and speech recognition in listeners with normal hearing and with hearing loss. Narrowband spectral resolution was assessed using auditory filter bandwidths estimated from simultaneous notched-noise masking. Broadband spectral processing was measured using the spectral ripple discrimination (SRD) task and the spectral ripple depth detection (SMD) task. Three different measures were used to assess unamplified and amplified speech recognition in quiet and noise. Stepwise multiple linear regression revealed that SMD at 2.0 cycles per octave (cpo) significantly predicted speech scores for amplified and unamplified speech in quiet and noise. Commonality analyses revealed that SMD at 2.0 cpo combined with SRD and equivalent rectangular bandwidth measures to explain most of the variance captured by the regression model. Results suggest that SMD and SRD may be promising clinical tools for diagnostic evaluation and predicting amplification outcomes.

Automatic Method of Pause Measurement for Normal and Dysarthric Speech

ERIC Educational Resources Information Center

Rosen, Kristin; Murdoch, Bruce; Folker, Joanne; Vogel, Adam; Cahill, Louise; Delatycki, Martin; Corben, Louise

2010-01-01

This study proposes an automatic method for the detection of pauses and identification of pause types in conversational speech for the purpose of measuring the effects of Friedreich's Ataxia (FRDA) on speech. Speech samples of [approximately] 3 minutes were recorded from 13 speakers with FRDA and 18 healthy controls. Pauses were measured from the…

Microscopic prediction of speech recognition for listeners with normal hearing in noise using an auditory model.

PubMed

Jürgens, Tim; Brand, Thomas

2009-11-01

This study compares the phoneme recognition performance in speech-shaped noise of a microscopic model for speech recognition with the performance of normal-hearing listeners. "Microscopic" is defined in terms of this model twofold. First, the speech recognition rate is predicted on a phoneme-by-phoneme basis. Second, microscopic modeling means that the signal waveforms to be recognized are processed by mimicking elementary parts of human's auditory processing. The model is based on an approach by Holube and Kollmeier [J. Acoust. Soc. Am. 100, 1703-1716 (1996)] and consists of a psychoacoustically and physiologically motivated preprocessing and a simple dynamic-time-warp speech recognizer. The model is evaluated while presenting nonsense speech in a closed-set paradigm. Averaged phoneme recognition rates, specific phoneme recognition rates, and phoneme confusions are analyzed. The influence of different perceptual distance measures and of the model's a-priori knowledge is investigated. The results show that human performance can be predicted by this model using an optimal detector, i.e., identical speech waveforms for both training of the recognizer and testing. The best model performance is yielded by distance measures which focus mainly on small perceptual distances and neglect outliers.

The influence of speech rate and accent on access and use of semantic information.

PubMed

Sajin, Stanislav M; Connine, Cynthia M

2017-04-01

Circumstances in which the speech input is presented in sub-optimal conditions generally lead to processing costs affecting spoken word recognition. The current study indicates that some processing demands imposed by listening to difficult speech can be mitigated by feedback from semantic knowledge. A set of lexical decision experiments examined how foreign accented speech and word duration impact access to semantic knowledge in spoken word recognition. Results indicate that when listeners process accented speech, the reliance on semantic information increases. Speech rate was not observed to influence semantic access, except in the setting in which unusually slow accented speech was presented. These findings support interactive activation models of spoken word recognition in which attention is modulated based on speech demands.

Use of intonation contours for speech recognition in noise by cochlear implant recipients.

PubMed

Meister, Hartmut; Landwehr, Markus; Pyschny, Verena; Grugel, Linda; Walger, Martin

2011-05-01

The corruption of intonation contours has detrimental effects on sentence-based speech recognition in normal-hearing listeners Binns and Culling [(2007). J. Acoust. Soc. Am. 122, 1765-1776]. This paper examines whether this finding also applies to cochlear implant (CI) recipients. The subjects' F0-discrimination and speech perception in the presence of noise were measured, using sentences with regular and inverted F0-contours. The results revealed that speech recognition for regular contours was significantly better than for inverted contours. This difference was related to the subjects' F0-discrimination providing further evidence that the perception of intonation patterns is important for the CI-mediated speech recognition in noise.

Does quality of life depend on speech recognition performance for adult cochlear implant users?

PubMed

Capretta, Natalie R; Moberly, Aaron C

2016-03-01

Current postoperative clinical outcome measures for adults receiving cochlear implants (CIs) consist of testing speech recognition, primarily under quiet conditions. However, it is strongly suspected that results on these measures may not adequately reflect patients' quality of life (QOL) using their implants. This study aimed to evaluate whether QOL for CI users depends on speech recognition performance. Twenty-three postlingually deafened adults with CIs were assessed. Participants were tested for speech recognition (Central Institute for the Deaf word and AzBio sentence recognition in quiet) and completed three QOL measures-the Nijmegen Cochlear Implant Questionnaire; either the Hearing Handicap Inventory for Adults or the Hearing Handicap Inventory for the Elderly; and the Speech, Spatial and Qualities of Hearing Scale questionnaires-to assess a variety of QOL factors. Correlations were sought between speech recognition and QOL scores. Demographics, audiologic history, language, and cognitive skills were also examined as potential predictors of QOL. Only a few QOL scores significantly correlated with postoperative sentence or word recognition in quiet, and correlations were primarily isolated to speech-related subscales on QOL measures. Poorer pre- and postoperative unaided hearing predicted better QOL. Socioeconomic status, duration of deafness, age at implantation, duration of CI use, reading ability, vocabulary size, and cognitive status did not consistently predict QOL scores. For adult, postlingually deafened CI users, clinical speech recognition measures in quiet do not correlate broadly with QOL. Results suggest the need for additional outcome measures of the benefits and limitations of cochlear implantation. 4. Laryngoscope, 126:699-706, 2016. © 2015 The American Laryngological, Rhinological and Otological Society, Inc.

Visual abilities are important for auditory-only speech recognition: evidence from autism spectrum disorder.

PubMed

Schelinski, Stefanie; Riedel, Philipp; von Kriegstein, Katharina

2014-12-01

In auditory-only conditions, for example when we listen to someone on the phone, it is essential to fast and accurately recognize what is said (speech recognition). Previous studies have shown that speech recognition performance in auditory-only conditions is better if the speaker is known not only by voice, but also by face. Here, we tested the hypothesis that such an improvement in auditory-only speech recognition depends on the ability to lip-read. To test this we recruited a group of adults with autism spectrum disorder (ASD), a condition associated with difficulties in lip-reading, and typically developed controls. All participants were trained to identify six speakers by name and voice. Three speakers were learned by a video showing their face and three others were learned in a matched control condition without face. After training, participants performed an auditory-only speech recognition test that consisted of sentences spoken by the trained speakers. As a control condition, the test also included speaker identity recognition on the same auditory material. The results showed that, in the control group, performance in speech recognition was improved for speakers known by face in comparison to speakers learned in the matched control condition without face. The ASD group lacked such a performance benefit. For the ASD group auditory-only speech recognition was even worse for speakers known by face compared to speakers not known by face. In speaker identity recognition, the ASD group performed worse than the control group independent of whether the speakers were learned with or without face. Two additional visual experiments showed that the ASD group performed worse in lip-reading whereas face identity recognition was within the normal range. The findings support the view that auditory-only communication involves specific visual mechanisms. Further, they indicate that in ASD, speaker-specific dynamic visual information is not available to optimize auditory-only speech recognition. Copyright © 2014 Elsevier Ltd. All rights reserved.

A constraint-based evolutionary learning approach to the expectation maximization for optimal estimation of the hidden Markov model for speech signal modeling.

PubMed

Huda, Shamsul; Yearwood, John; Togneri, Roberto

2009-02-01

This paper attempts to overcome the tendency of the expectation-maximization (EM) algorithm to locate a local rather than global maximum when applied to estimate the hidden Markov model (HMM) parameters in speech signal modeling. We propose a hybrid algorithm for estimation of the HMM in automatic speech recognition (ASR) using a constraint-based evolutionary algorithm (EA) and EM, the CEL-EM. The novelty of our hybrid algorithm (CEL-EM) is that it is applicable for estimation of the constraint-based models with many constraints and large numbers of parameters (which use EM) like HMM. Two constraint-based versions of the CEL-EM with different fusion strategies have been proposed using a constraint-based EA and the EM for better estimation of HMM in ASR. The first one uses a traditional constraint-handling mechanism of EA. The other version transforms a constrained optimization problem into an unconstrained problem using Lagrange multipliers. Fusion strategies for the CEL-EM use a staged-fusion approach where EM has been plugged with the EA periodically after the execution of EA for a specific period of time to maintain the global sampling capabilities of EA in the hybrid algorithm. A variable initialization approach (VIA) has been proposed using a variable segmentation to provide a better initialization for EA in the CEL-EM. Experimental results on the TIMIT speech corpus show that CEL-EM obtains higher recognition accuracies than the traditional EM algorithm as well as a top-standard EM (VIA-EM, constructed by applying the VIA to EM).

Speech processing using maximum likelihood continuity mapping

DOEpatents

Hogden, John E.

2000-01-01

Speech processing is obtained that, given a probabilistic mapping between static speech sounds and pseudo-articulator positions, allows sequences of speech sounds to be mapped to smooth sequences of pseudo-articulator positions. In addition, a method for learning a probabilistic mapping between static speech sounds and pseudo-articulator position is described. The method for learning the mapping between static speech sounds and pseudo-articulator position uses a set of training data composed only of speech sounds. The said speech processing can be applied to various speech analysis tasks, including speech recognition, speaker recognition, speech coding, speech synthesis, and voice mimicry.

Speech processing using maximum likelihood continuity mapping

DOE Office of Scientific and Technical Information (OSTI.GOV)

Hogden, J.E.

Speech processing is obtained that, given a probabilistic mapping between static speech sounds and pseudo-articulator positions, allows sequences of speech sounds to be mapped to smooth sequences of pseudo-articulator positions. In addition, a method for learning a probabilistic mapping between static speech sounds and pseudo-articulator position is described. The method for learning the mapping between static speech sounds and pseudo-articulator position uses a set of training data composed only of speech sounds. The said speech processing can be applied to various speech analysis tasks, including speech recognition, speaker recognition, speech coding, speech synthesis, and voice mimicry.

Supporting Dictation Speech Recognition Error Correction: The Impact of External Information

ERIC Educational Resources Information Center

Shi, Yongmei; Zhou, Lina

2011-01-01

Although speech recognition technology has made remarkable progress, its wide adoption is still restricted by notable effort made and frustration experienced by users while correcting speech recognition errors. One of the promising ways to improve error correction is by providing user support. Although support mechanisms have been proposed for…

Application of an auditory model to speech recognition.

PubMed

Cohen, J R

1989-06-01

Some aspects of auditory processing are incorporated in a front end for the IBM speech-recognition system [F. Jelinek, "Continuous speech recognition by statistical methods," Proc. IEEE 64 (4), 532-556 (1976)]. This new process includes adaptation, loudness scaling, and mel warping. Tests show that the design is an improvement over previous algorithms.

Breaking the language barrier: machine assisted diagnosis using the medical speech translator.

PubMed

Starlander, Marianne; Bouillon, Pierrette; Rayner, Manny; Chatzichrisafis, Nikos; Hockey, Beth Ann; Isahara, Hitoshi; Kanzaki, Kyoko; Nakao, Yukie; Santaholma, Marianne

2005-01-01

In this paper, we describe and evaluate an Open Source medical speech translation system (MedSLT) intended for safety-critical applications. The aim of this system is to eliminate the language barriers in emergency situation. It translates spoken questions from English into French, Japanese and Finnish in three medical subdomains (headache, chest pain and abdominal pain), using a vocabulary of about 250-400 words per sub-domain. The architecture is a compromise between fixed-phrase translation on one hand and complex linguistically-based systems on the other. Recognition is guided by a Context Free Grammar Language Model compiled from a general unification grammar, automatically specialised for the domain. We present an evaluation of this initial prototype that shows the advantages of this grammar-based approach for this particular translation task in term of both reliability and use.

Influence of phonetic context on the dysphonic event: contribution of new methodologies for the analysis of pathological voice.

PubMed

Revis, J; Galant, C; Fredouille, C; Ghio, A; Giovanni, A

2012-01-01

Widely studied in terms of perception, acoustics or aerodynamics, dysphonia stays nevertheless a speech phenomenon, closely related to the phonetic composition of the message conveyed by the voice. In this paper, we present a series of three works with the aim to understand the implications of the phonetic manifestation of dysphonia. Our first study proposes a new approach to the perceptual analysis of dysphonia (the phonetic labeling), which principle is to listen and evaluate each phoneme in a sentence separately. This study confirms the hypothesis of Laver that the dysphonia is not a constant noise added to the speech signal, but a discontinuous phenomenon, occurring on certain phonemes, based on the phonetic context. However, the burden of executing the task has led us to look to the techniques of automatic speaker recognition (ASR) to automate the procedure. With the collaboration of the LIA, we have developed a system for automatic classification of dysphonia from the techniques of ASR. This is the subject of our second study. The first results obtained with this system suggest that the unvoiced consonants show predominant performance in the task of automatic classification of dysphonia. This result is surprising since it is often assumed that dysphonia occurs only on laryngeal vibration. We started looking for explanations of this phenomenon and we present our assumptions and experiences in the third work we present.

Automatic detection of Parkinson's disease in running speech spoken in three different languages.

PubMed

Orozco-Arroyave, J R; Hönig, F; Arias-Londoño, J D; Vargas-Bonilla, J F; Daqrouq, K; Skodda, S; Rusz, J; Nöth, E

2016-01-01

The aim of this study is the analysis of continuous speech signals of people with Parkinson's disease (PD) considering recordings in different languages (Spanish, German, and Czech). A method for the characterization of the speech signals, based on the automatic segmentation of utterances into voiced and unvoiced frames, is addressed here. The energy content of the unvoiced sounds is modeled using 12 Mel-frequency cepstral coefficients and 25 bands scaled according to the Bark scale. Four speech tasks comprising isolated words, rapid repetition of the syllables /pa/-/ta/-/ka/, sentences, and read texts are evaluated. The method proves to be more accurate than classical approaches in the automatic classification of speech of people with PD and healthy controls. The accuracies range from 85% to 99% depending on the language and the speech task. Cross-language experiments are also performed confirming the robustness and generalization capability of the method, with accuracies ranging from 60% to 99%. This work comprises a step forward for the development of computer aided tools for the automatic assessment of dysarthric speech signals in multiple languages.

Increase in Speech Recognition Due to Linguistic Mismatch between Target and Masker Speech: Monolingual and Simultaneous Bilingual Performance

ERIC Educational Resources Information Center

Calandruccio, Lauren; Zhou, Haibo

2014-01-01

Purpose: To examine whether improved speech recognition during linguistically mismatched target-masker experiments is due to linguistic unfamiliarity of the masker speech or linguistic dissimilarity between the target and masker speech. Method: Monolingual English speakers (n = 20) and English-Greek simultaneous bilinguals (n = 20) listened to…

The influence of audibility on speech recognition with nonlinear frequency compression for children and adults with hearing loss

PubMed Central

McCreery, Ryan W.; Alexander, Joshua; Brennan, Marc A.; Hoover, Brenda; Kopun, Judy; Stelmachowicz, Patricia G.

2014-01-01

Objective The primary goal of nonlinear frequency compression (NFC) and other frequency lowering strategies is to increase the audibility of high-frequency sounds that are not otherwise audible with conventional hearing-aid processing due to the degree of hearing loss, limited hearing aid bandwidth or a combination of both factors. The aim of the current study was to compare estimates of speech audibility processed by NFC to improvements in speech recognition for a group of children and adults with high-frequency hearing loss. Design Monosyllabic word recognition was measured in noise for twenty-four adults and twelve children with mild to severe sensorineural hearing loss. Stimuli were amplified based on each listener’s audiogram with conventional processing (CP) with amplitude compression or with NFC and presented under headphones using a software-based hearing aid simulator. A modification of the speech intelligibility index (SII) was used to estimate audibility of information in frequency-lowered bands. The mean improvement in SII was compared to the mean improvement in speech recognition. Results All but two listeners experienced improvements in speech recognition with NFC compared to CP, consistent with the small increase in audibility that was estimated using the modification of the SII. Children and adults had similar improvements in speech recognition with NFC. Conclusion Word recognition with NFC was higher than CP for children and adults with mild to severe hearing loss. The average improvement in speech recognition with NFC (7%) was consistent with the modified SII, which indicated that listeners experienced an increase in audibility with NFC compared to CP. Further studies are necessary to determine if changes in audibility with NFC are related to speech recognition with NFC for listeners with greater degrees of hearing loss, with a greater variety of compression settings, and using auditory training. PMID:24535558

How much does language proficiency by non-native listeners influence speech audiometric tests in noise?

PubMed

Warzybok, Anna; Brand, Thomas; Wagener, Kirsten C; Kollmeier, Birger

2015-01-01

The current study investigates the extent to which the linguistic complexity of three commonly employed speech recognition tests and second language proficiency influence speech recognition thresholds (SRTs) in noise in non-native listeners. SRTs were measured for non-natives and natives using three German speech recognition tests: the digit triplet test (DTT), the Oldenburg sentence test (OLSA), and the Göttingen sentence test (GÖSA). Sixty-four non-native and eight native listeners participated. Non-natives can show native-like SRTs in noise only for the linguistically easy speech material (DTT). Furthermore, the limitation of phonemic-acoustical cues in digit triplets affects speech recognition to the same extent in non-natives and natives. For more complex and less familiar speech materials, non-natives, ranging from basic to advanced proficiency in German, require on average 3-dB better signal-to-noise ratio for the OLSA and 6-dB for the GÖSA to obtain 50% speech recognition compared to native listeners. In clinical audiology, SRT measurements with a closed-set speech test (i.e. DTT for screening or OLSA test for clinical purposes) should be used with non-native listeners rather than open-set speech tests (such as the GÖSA or HINT), especially if a closed-set version in the patient's own native language is available.

Mandarin-Speaking Children's Speech Recognition: Developmental Changes in the Influences of Semantic Context and F0 Contours.

PubMed

Zhou, Hong; Li, Yu; Liang, Meng; Guan, Connie Qun; Zhang, Linjun; Shu, Hua; Zhang, Yang

2017-01-01

The goal of this developmental speech perception study was to assess whether and how age group modulated the influences of high-level semantic context and low-level fundamental frequency ( F 0 ) contours on the recognition of Mandarin speech by elementary and middle-school-aged children in quiet and interference backgrounds. The results revealed different patterns for semantic and F 0 information. One the one hand, age group modulated significantly the use of F 0 contours, indicating that elementary school children relied more on natural F 0 contours than middle school children during Mandarin speech recognition. On the other hand, there was no significant modulation effect of age group on semantic context, indicating that children of both age groups used semantic context to assist speech recognition to a similar extent. Furthermore, the significant modulation effect of age group on the interaction between F 0 contours and semantic context revealed that younger children could not make better use of semantic context in recognizing speech with flat F 0 contours compared with natural F 0 contours, while older children could benefit from semantic context even when natural F 0 contours were altered, thus confirming the important role of F 0 contours in Mandarin speech recognition by elementary school children. The developmental changes in the effects of high-level semantic and low-level F 0 information on speech recognition might reflect the differences in auditory and cognitive resources associated with processing of the two types of information in speech perception.

Talker variability in audio-visual speech perception

PubMed Central

Heald, Shannon L. M.; Nusbaum, Howard C.

2014-01-01

A change in talker is a change in the context for the phonetic interpretation of acoustic patterns of speech. Different talkers have different mappings between acoustic patterns and phonetic categories and listeners need to adapt to these differences. Despite this complexity, listeners are adept at comprehending speech in multiple-talker contexts, albeit at a slight but measurable performance cost (e.g., slower recognition). So far, this talker variability cost has been demonstrated only in audio-only speech. Other research in single-talker contexts have shown, however, that when listeners are able to see a talker’s face, speech recognition is improved under adverse listening (e.g., noise or distortion) conditions that can increase uncertainty in the mapping between acoustic patterns and phonetic categories. Does seeing a talker’s face reduce the cost of word recognition in multiple-talker contexts? We used a speeded word-monitoring task in which listeners make quick judgments about target word recognition in single- and multiple-talker contexts. Results show faster recognition performance in single-talker conditions compared to multiple-talker conditions for both audio-only and audio-visual speech. However, recognition time in a multiple-talker context was slower in the audio-visual condition compared to audio-only condition. These results suggest that seeing a talker’s face during speech perception may slow recognition by increasing the importance of talker identification, signaling to the listener a change in talker has occurred. PMID:25076919

Talker variability in audio-visual speech perception.

PubMed

Heald, Shannon L M; Nusbaum, Howard C

2014-01-01

A change in talker is a change in the context for the phonetic interpretation of acoustic patterns of speech. Different talkers have different mappings between acoustic patterns and phonetic categories and listeners need to adapt to these differences. Despite this complexity, listeners are adept at comprehending speech in multiple-talker contexts, albeit at a slight but measurable performance cost (e.g., slower recognition). So far, this talker variability cost has been demonstrated only in audio-only speech. Other research in single-talker contexts have shown, however, that when listeners are able to see a talker's face, speech recognition is improved under adverse listening (e.g., noise or distortion) conditions that can increase uncertainty in the mapping between acoustic patterns and phonetic categories. Does seeing a talker's face reduce the cost of word recognition in multiple-talker contexts? We used a speeded word-monitoring task in which listeners make quick judgments about target word recognition in single- and multiple-talker contexts. Results show faster recognition performance in single-talker conditions compared to multiple-talker conditions for both audio-only and audio-visual speech. However, recognition time in a multiple-talker context was slower in the audio-visual condition compared to audio-only condition. These results suggest that seeing a talker's face during speech perception may slow recognition by increasing the importance of talker identification, signaling to the listener a change in talker has occurred.

Comparison of Classification Methods for Detecting Emotion from Mandarin Speech

NASA Astrophysics Data System (ADS)

Pao, Tsang-Long; Chen, Yu-Te; Yeh, Jun-Heng

It is said that technology comes out from humanity. What is humanity? The very definition of humanity is emotion. Emotion is the basis for all human expression and the underlying theme behind everything that is done, said, thought or imagined. Making computers being able to perceive and respond to human emotion, the human-computer interaction will be more natural. Several classifiers are adopted for automatically assigning an emotion category, such as anger, happiness or sadness, to a speech utterance. These classifiers were designed independently and tested on various emotional speech corpora, making it difficult to compare and evaluate their performance. In this paper, we first compared several popular classification methods and evaluated their performance by applying them to a Mandarin speech corpus consisting of five basic emotions, including anger, happiness, boredom, sadness and neutral. The extracted feature streams contain MFCC, LPCC, and LPC. The experimental results show that the proposed WD-MKNN classifier achieves an accuracy of 81.4% for the 5-class emotion recognition and outperforms other classification techniques, including KNN, MKNN, DW-KNN, LDA, QDA, GMM, HMM, SVM, and BPNN. Then, to verify the advantage of the proposed method, we compared these classifiers by applying them to another Mandarin expressive speech corpus consisting of two emotions. The experimental results still show that the proposed WD-MKNN outperforms others.

Methods and apparatus for non-acoustic speech characterization and recognition

DOEpatents

Holzrichter, John F.

1999-01-01

By simultaneously recording EM wave reflections and acoustic speech information, the positions and velocities of the speech organs as speech is articulated can be defined for each acoustic speech unit. Well defined time frames and feature vectors describing the speech, to the degree required, can be formed. Such feature vectors can uniquely characterize the speech unit being articulated each time frame. The onset of speech, rejection of external noise, vocalized pitch periods, articulator conditions, accurate timing, the identification of the speaker, acoustic speech unit recognition, and organ mechanical parameters can be determined.

Methods and apparatus for non-acoustic speech characterization and recognition

DOE Office of Scientific and Technical Information (OSTI.GOV)

Holzrichter, J.F.

By simultaneously recording EM wave reflections and acoustic speech information, the positions and velocities of the speech organs as speech is articulated can be defined for each acoustic speech unit. Well defined time frames and feature vectors describing the speech, to the degree required, can be formed. Such feature vectors can uniquely characterize the speech unit being articulated each time frame. The onset of speech, rejection of external noise, vocalized pitch periods, articulator conditions, accurate timing, the identification of the speaker, acoustic speech unit recognition, and organ mechanical parameters can be determined.

Measures of voiced frication for automatic classification

NASA Astrophysics Data System (ADS)

Jackson, Philip J. B.; Jesus, Luis M. T.; Shadle, Christine H.; Pincas, Jonathan

2004-05-01

As an approach to understanding the characteristics of the acoustic sources in voiced fricatives, it seems apt to draw on knowledge of vowels and voiceless fricatives, which have been relatively well studied. However, the presence of both phonation and frication in these mixed-source sounds offers the possibility of mutual interaction effects, with variations across place of articulation. This paper examines the acoustic and articulatory consequences of these interactions and explores automatic techniques for finding parametric and statistical descriptions of these phenomena. A reliable and consistent set of such acoustic cues could be used for phonetic classification or speech recognition. Following work on devoicing of European Portuguese voiced fricatives [Jesus and Shadle, in Mamede et al. (eds.) (Springer-Verlag, Berlin, 2003), pp. 1-8]. and the modulating effect of voicing on frication [Jackson and Shadle, J. Acoust. Soc. Am. 108, 1421-1434 (2000)], the present study focuses on three types of information: (i) sequences and durations of acoustic events in VC transitions, (ii) temporal, spectral and modulation measures from the periodic and aperiodic components of the acoustic signal, and (iii) voicing activity derived from simultaneous EGG data. Analysis of interactions observed in British/American English and European Portuguese speech corpora will be compared, and the principal findings discussed.

Effects of Age and Working Memory Capacity on Speech Recognition Performance in Noise Among Listeners With Normal Hearing.

PubMed

Gordon-Salant, Sandra; Cole, Stacey Samuels

2016-01-01

This study aimed to determine if younger and older listeners with normal hearing who differ on working memory span perform differently on speech recognition tests in noise. Older adults typically exhibit poorer speech recognition scores in noise than younger adults, which is attributed primarily to poorer hearing sensitivity and more limited working memory capacity in older than younger adults. Previous studies typically tested older listeners with poorer hearing sensitivity and shorter working memory spans than younger listeners, making it difficult to discern the importance of working memory capacity on speech recognition. This investigation controlled for hearing sensitivity and compared speech recognition performance in noise by younger and older listeners who were subdivided into high and low working memory groups. Performance patterns were compared for different speech materials to assess whether or not the effect of working memory capacity varies with the demands of the specific speech test. The authors hypothesized that (1) normal-hearing listeners with low working memory span would exhibit poorer speech recognition performance in noise than those with high working memory span; (2) older listeners with normal hearing would show poorer speech recognition scores than younger listeners with normal hearing, when the two age groups were matched for working memory span; and (3) an interaction between age and working memory would be observed for speech materials that provide contextual cues. Twenty-eight older (61 to 75 years) and 25 younger (18 to 25 years) normal-hearing listeners were assigned to groups based on age and working memory status. Northwestern University Auditory Test No. 6 words and Institute of Electrical and Electronics Engineers sentences were presented in noise using an adaptive procedure to measure the signal-to-noise ratio corresponding to 50% correct performance. Cognitive ability was evaluated with two tests of working memory (Listening Span Test and Reading Span Test) and two tests of processing speed (Paced Auditory Serial Addition Test and The Letter Digit Substitution Test). Significant effects of age and working memory capacity were observed on the speech recognition measures in noise, but these effects were mediated somewhat by the speech signal. Specifically, main effects of age and working memory were revealed for both words and sentences, but the interaction between the two was significant for sentences only. For these materials, effects of age were observed for listeners in the low working memory groups only. Although all cognitive measures were significantly correlated with speech recognition in noise, working memory span was the most important variable accounting for speech recognition performance. The results indicate that older adults with high working memory capacity are able to capitalize on contextual cues and perform as well as young listeners with high working memory capacity for sentence recognition. The data also suggest that listeners with normal hearing and low working memory capacity are less able to adapt to distortion of speech signals caused by background noise, which requires the allocation of more processing resources to earlier processing stages. These results indicate that both younger and older adults with low working memory capacity and normal hearing are at a disadvantage for recognizing speech in noise.

Speech Recognition and Cognitive Skills in Bimodal Cochlear Implant Users

ERIC Educational Resources Information Center

Hua, Håkan; Johansson, Björn; Magnusson, Lennart; Lyxell, Björn; Ellis, Rachel J.

2017-01-01

Purpose: To examine the relation between speech recognition and cognitive skills in bimodal cochlear implant (CI) and hearing aid users. Method: Seventeen bimodal CI users (28-74 years) were recruited to the study. Speech recognition tests were carried out in quiet and in noise. The cognitive tests employed included the Reading Span Test and the…

Visual Speech Primes Open-Set Recognition of Spoken Words

ERIC Educational Resources Information Center

Buchwald, Adam B.; Winters, Stephen J.; Pisoni, David B.

2009-01-01

Visual speech perception has become a topic of considerable interest to speech researchers. Previous research has demonstrated that perceivers neurally encode and use speech information from the visual modality, and this information has been found to facilitate spoken word recognition in tasks such as lexical decision (Kim, Davis, & Krins,…

Significance of parametric spectral ratio methods in detection and recognition of whispered speech

NASA Astrophysics Data System (ADS)

Mathur, Arpit; Reddy, Shankar M.; Hegde, Rajesh M.

2012-12-01

In this article the significance of a new parametric spectral ratio method that can be used to detect whispered speech segments within normally phonated speech is described. Adaptation methods based on the maximum likelihood linear regression (MLLR) are then used to realize a mismatched train-test style speech recognition system. This proposed parametric spectral ratio method computes a ratio spectrum of the linear prediction (LP) and the minimum variance distortion-less response (MVDR) methods. The smoothed ratio spectrum is then used to detect whispered segments of speech within neutral speech segments effectively. The proposed LP-MVDR ratio method exhibits robustness at different SNRs as indicated by the whisper diarization experiments conducted on the CHAINS and the cell phone whispered speech corpus. The proposed method also performs reasonably better than the conventional methods for whisper detection. In order to integrate the proposed whisper detection method into a conventional speech recognition engine with minimal changes, adaptation methods based on the MLLR are used herein. The hidden Markov models corresponding to neutral mode speech are adapted to the whispered mode speech data in the whispered regions as detected by the proposed ratio method. The performance of this method is first evaluated on whispered speech data from the CHAINS corpus. The second set of experiments are conducted on the cell phone corpus of whispered speech. This corpus is collected using a set up that is used commercially for handling public transactions. The proposed whisper speech recognition system exhibits reasonably better performance when compared to several conventional methods. The results shown indicate the possibility of a whispered speech recognition system for cell phone based transactions.

Current trends in small vocabulary speech recognition for equipment control

NASA Astrophysics Data System (ADS)

Doukas, Nikolaos; Bardis, Nikolaos G.

2017-09-01

Speech recognition systems allow human - machine communication to acquire an intuitive nature that approaches the simplicity of inter - human communication. Small vocabulary speech recognition is a subset of the overall speech recognition problem, where only a small number of words need to be recognized. Speaker independent small vocabulary recognition can find significant applications in field equipment used by military personnel. Such equipment may typically be controlled by a small number of commands that need to be given quickly and accurately, under conditions where delicate manual operations are difficult to achieve. This type of application could hence significantly benefit by the use of robust voice operated control components, as they would facilitate the interaction with their users and render it much more reliable in times of crisis. This paper presents current challenges involved in attaining efficient and robust small vocabulary speech recognition. These challenges concern feature selection, classification techniques, speaker diversity and noise effects. A state machine approach is presented that facilitates the voice guidance of different equipment in a variety of situations.

Preschoolers Benefit From Visually Salient Speech Cues

PubMed Central

Holt, Rachael Frush

2015-01-01

Purpose This study explored visual speech influence in preschoolers using 3 developmentally appropriate tasks that vary in perceptual difficulty and task demands. They also examined developmental differences in the ability to use visually salient speech cues and visual phonological knowledge. Method Twelve adults and 27 typically developing 3- and 4-year-old children completed 3 audiovisual (AV) speech integration tasks: matching, discrimination, and recognition. The authors compared AV benefit for visually salient and less visually salient speech discrimination contrasts and assessed the visual saliency of consonant confusions in auditory-only and AV word recognition. Results Four-year-olds and adults demonstrated visual influence on all measures. Three-year-olds demonstrated visual influence on speech discrimination and recognition measures. All groups demonstrated greater AV benefit for the visually salient discrimination contrasts. AV recognition benefit in 4-year-olds and adults depended on the visual saliency of speech sounds. Conclusions Preschoolers can demonstrate AV speech integration. Their AV benefit results from efficient use of visually salient speech cues. Four-year-olds, but not 3-year-olds, used visual phonological knowledge to take advantage of visually salient speech cues, suggesting possible developmental differences in the mechanisms of AV benefit. PMID:25322336

Action Unit Models of Facial Expression of Emotion in the Presence of Speech

PubMed Central

Shah, Miraj; Cooper, David G.; Cao, Houwei; Gur, Ruben C.; Nenkova, Ani; Verma, Ragini

2014-01-01

Automatic recognition of emotion using facial expressions in the presence of speech poses a unique challenge because talking reveals clues for the affective state of the speaker but distorts the canonical expression of emotion on the face. We introduce a corpus of acted emotion expression where speech is either present (talking) or absent (silent). The corpus is uniquely suited for analysis of the interplay between the two conditions. We use a multimodal decision level fusion classifier to combine models of emotion from talking and silent faces as well as from audio to recognize five basic emotions: anger, disgust, fear, happy and sad. Our results strongly indicate that emotion prediction in the presence of speech from action unit facial features is less accurate when the person is talking. Modeling talking and silent expressions separately and fusing the two models greatly improves accuracy of prediction in the talking setting. The advantages are most pronounced when silent and talking face models are fused with predictions from audio features. In this multi-modal prediction both the combination of modalities and the separate models of talking and silent facial expression of emotion contribute to the improvement. PMID:25525561

Speech Perception in Noise by Children With Cochlear Implants

PubMed Central

Caldwell, Amanda; Nittrouer, Susan

2013-01-01

Purpose Common wisdom suggests that listening in noise poses disproportionately greater difficulty for listeners with cochlear implants (CIs) than for peers with normal hearing (NH). The purpose of this study was to examine phonological, language, and cognitive skills that might help explain speech-in-noise abilities for children with CIs. Method Three groups of kindergartners (NH, hearing aid wearers, and CI users) were tested on speech recognition in quiet and noise and on tasks thought to underlie the abilities that fit into the domains of phonological awareness, general language, and cognitive skills. These last measures were used as predictor variables in regression analyses with speech-in-noise scores as dependent variables. Results Compared to children with NH, children with CIs did not perform as well on speech recognition in noise or on most other measures, including recognition in quiet. Two surprising results were that (a) noise effects were consistent across groups and (b) scores on other measures did not explain any group differences in speech recognition. Conclusions Limitations of implant processing take their primary toll on recognition in quiet and account for poor speech recognition and language/phonological deficits in children with CIs. Implications are that teachers/clinicians need to teach language/phonology directly and maximize signal-to-noise levels in the classroom. PMID:22744138

Simulation of talking faces in the human brain improves auditory speech recognition

PubMed Central

von Kriegstein, Katharina; Dogan, Özgür; Grüter, Martina; Giraud, Anne-Lise; Kell, Christian A.; Grüter, Thomas; Kleinschmidt, Andreas; Kiebel, Stefan J.

2008-01-01

Human face-to-face communication is essentially audiovisual. Typically, people talk to us face-to-face, providing concurrent auditory and visual input. Understanding someone is easier when there is visual input, because visual cues like mouth and tongue movements provide complementary information about speech content. Here, we hypothesized that, even in the absence of visual input, the brain optimizes both auditory-only speech and speaker recognition by harvesting speaker-specific predictions and constraints from distinct visual face-processing areas. To test this hypothesis, we performed behavioral and neuroimaging experiments in two groups: subjects with a face recognition deficit (prosopagnosia) and matched controls. The results show that observing a specific person talking for 2 min improves subsequent auditory-only speech and speaker recognition for this person. In both prosopagnosics and controls, behavioral improvement in auditory-only speech recognition was based on an area typically involved in face-movement processing. Improvement in speaker recognition was only present in controls and was based on an area involved in face-identity processing. These findings challenge current unisensory models of speech processing, because they show that, in auditory-only speech, the brain exploits previously encoded audiovisual correlations to optimize communication. We suggest that this optimization is based on speaker-specific audiovisual internal models, which are used to simulate a talking face. PMID:18436648

Methods for eliciting, annotating, and analyzing databases for child speech development.

PubMed

Beckman, Mary E; Plummer, Andrew R; Munson, Benjamin; Reidy, Patrick F

2017-09-01

Methods from automatic speech recognition (ASR), such as segmentation and forced alignment, have facilitated the rapid annotation and analysis of very large adult speech databases and databases of caregiver-infant interaction, enabling advances in speech science that were unimaginable just a few decades ago. This paper centers on two main problems that must be addressed in order to have analogous resources for developing and exploiting databases of young children's speech. The first problem is to understand and appreciate the differences between adult and child speech that cause ASR models developed for adult speech to fail when applied to child speech. These differences include the fact that children's vocal tracts are smaller than those of adult males and also changing rapidly in size and shape over the course of development, leading to between-talker variability across age groups that dwarfs the between-talker differences between adult men and women. Moreover, children do not achieve fully adult-like speech motor control until they are young adults, and their vocabularies and phonological proficiency are developing as well, leading to considerably more within-talker variability as well as more between-talker variability. The second problem then is to determine what annotation schemas and analysis techniques can most usefully capture relevant aspects of this variability. Indeed, standard acoustic characterizations applied to child speech reveal that adult-centered annotation schemas fail to capture phenomena such as the emergence of covert contrasts in children's developing phonological systems, while also revealing children's nonuniform progression toward community speech norms as they acquire the phonological systems of their native languages. Both problems point to the need for more basic research into the growth and development of the articulatory system (as well as of the lexicon and phonological system) that is oriented explicitly toward the construction of age-appropriate computational models.

Speech coding, reconstruction and recognition using acoustics and electromagnetic waves

DOEpatents

Holzrichter, J.F.; Ng, L.C.

1998-03-17

The use of EM radiation in conjunction with simultaneously recorded acoustic speech information enables a complete mathematical coding of acoustic speech. The methods include the forming of a feature vector for each pitch period of voiced speech and the forming of feature vectors for each time frame of unvoiced, as well as for combined voiced and unvoiced speech. The methods include how to deconvolve the speech excitation function from the acoustic speech output to describe the transfer function each time frame. The formation of feature vectors defining all acoustic speech units over well defined time frames can be used for purposes of speech coding, speech compression, speaker identification, language-of-speech identification, speech recognition, speech synthesis, speech translation, speech telephony, and speech teaching. 35 figs.

Speech coding, reconstruction and recognition using acoustics and electromagnetic waves

DOEpatents

Holzrichter, John F.; Ng, Lawrence C.

1998-01-01

The use of EM radiation in conjunction with simultaneously recorded acoustic speech information enables a complete mathematical coding of acoustic speech. The methods include the forming of a feature vector for each pitch period of voiced speech and the forming of feature vectors for each time frame of unvoiced, as well as for combined voiced and unvoiced speech. The methods include how to deconvolve the speech excitation function from the acoustic speech output to describe the transfer function each time frame. The formation of feature vectors defining all acoustic speech units over well defined time frames can be used for purposes of speech coding, speech compression, speaker identification, language-of-speech identification, speech recognition, speech synthesis, speech translation, speech telephony, and speech teaching.

Characteristics of speaking style and implications for speech recognition.

PubMed

Shinozaki, Takahiro; Ostendorf, Mari; Atlas, Les

2009-09-01

Differences in speaking style are associated with more or less spectral variability, as well as different modulation characteristics. The greater variation in some styles (e.g., spontaneous speech and infant-directed speech) poses challenges for recognition but possibly also opportunities for learning more robust models, as evidenced by prior work and motivated by child language acquisition studies. In order to investigate this possibility, this work proposes a new method for characterizing speaking style (the modulation spectrum), examines spontaneous, read, adult-directed, and infant-directed styles in this space, and conducts pilot experiments in style detection and sampling for improved speech recognizer training. Speaking style classification is improved by using the modulation spectrum in combination with standard pitch and energy variation. Speech recognition experiments on a small vocabulary conversational speech recognition task show that sampling methods for training with a small amount of data benefit from the new features.

Evaluation of Speech Recognition of Cochlear Implant Recipients Using Adaptive, Digital Remote Microphone Technology and a Speech Enhancement Sound Processing Algorithm.

PubMed

Wolfe, Jace; Morais, Mila; Schafer, Erin; Agrawal, Smita; Koch, Dawn

2015-05-01

Cochlear implant recipients often experience difficulty with understanding speech in the presence of noise. Cochlear implant manufacturers have developed sound processing algorithms designed to improve speech recognition in noise, and research has shown these technologies to be effective. Remote microphone technology utilizing adaptive, digital wireless radio transmission has also been shown to provide significant improvement in speech recognition in noise. There are no studies examining the potential improvement in speech recognition in noise when these two technologies are used simultaneously. The goal of this study was to evaluate the potential benefits and limitations associated with the simultaneous use of a sound processing algorithm designed to improve performance in noise (Advanced Bionics ClearVoice) and a remote microphone system that incorporates adaptive, digital wireless radio transmission (Phonak Roger). A two-by-two way repeated measures design was used to examine performance differences obtained without these technologies compared to the use of each technology separately as well as the simultaneous use of both technologies. Eleven Advanced Bionics (AB) cochlear implant recipients, ages 11 to 68 yr. AzBio sentence recognition was measured in quiet and in the presence of classroom noise ranging in level from 50 to 80 dBA in 5-dB steps. Performance was evaluated in four conditions: (1) No ClearVoice and no Roger, (2) ClearVoice enabled without the use of Roger, (3) ClearVoice disabled with Roger enabled, and (4) simultaneous use of ClearVoice and Roger. Speech recognition in quiet was better than speech recognition in noise for all conditions. Use of ClearVoice and Roger each provided significant improvement in speech recognition in noise. The best performance in noise was obtained with the simultaneous use of ClearVoice and Roger. ClearVoice and Roger technology each improves speech recognition in noise, particularly when used at the same time. Because ClearVoice does not degrade performance in quiet settings, clinicians should consider recommending ClearVoice for routine, full-time use for AB implant recipients. Roger should be used in all instances in which remote microphone technology may assist the user in understanding speech in the presence of noise. American Academy of Audiology.

Speech recognition: how good is good enough?

PubMed

Krohn, Richard

2002-03-01

Since its infancy in the early 1990s, the technology of speech recognition has undergone a rapid evolution. Not only has the reliability of the programming improved dramatically, the return on investment has become increasingly compelling. The author describes some of the latest health care applications of speech-recognition technology, and how the next advances will be made in this area.

Sensory Intelligence for Extraction of an Abstract Auditory Rule: A Cross-Linguistic Study.

PubMed

Guo, Xiao-Tao; Wang, Xiao-Dong; Liang, Xiu-Yuan; Wang, Ming; Chen, Lin

2018-02-21

In a complex linguistic environment, while speech sounds can greatly vary, some shared features are often invariant. These invariant features constitute so-called abstract auditory rules. Our previous study has shown that with auditory sensory intelligence, the human brain can automatically extract the abstract auditory rules in the speech sound stream, presumably serving as the neural basis for speech comprehension. However, whether the sensory intelligence for extraction of abstract auditory rules in speech is inherent or experience-dependent remains unclear. To address this issue, we constructed a complex speech sound stream using auditory materials in Mandarin Chinese, in which syllables had a flat lexical tone but differed in other acoustic features to form an abstract auditory rule. This rule was occasionally and randomly violated by the syllables with the rising, dipping or falling tone. We found that both Chinese and foreign speakers detected the violations of the abstract auditory rule in the speech sound stream at a pre-attentive stage, as revealed by the whole-head recordings of mismatch negativity (MMN) in a passive paradigm. However, MMNs peaked earlier in Chinese speakers than in foreign speakers. Furthermore, Chinese speakers showed different MMN peak latencies for the three deviant types, which paralleled recognition points. These findings indicate that the sensory intelligence for extraction of abstract auditory rules in speech sounds is innate but shaped by language experience. Copyright © 2018 IBRO. Published by Elsevier Ltd. All rights reserved.

The Swedish Hayling task, and its relation to working memory, verbal ability, and speech-recognition-in-noise.

PubMed

Stenbäck, Victoria; Hällgren, Mathias; Lyxell, Björn; Larsby, Birgitta

2015-06-01

Cognitive functions and speech-recognition-in-noise were evaluated with a cognitive test battery, assessing response inhibition using the Hayling task, working memory capacity (WMC) and verbal information processing, and an auditory test of speech recognition. The cognitive tests were performed in silence whereas the speech recognition task was presented in noise. Thirty young normally-hearing individuals participated in the study. The aim of the study was to investigate one executive function, response inhibition, and whether it is related to individual working memory capacity (WMC), and how speech-recognition-in-noise relates to WMC and inhibitory control. The results showed a significant difference between initiation and response inhibition, suggesting that the Hayling task taps cognitive activity responsible for executive control. Our findings also suggest that high verbal ability was associated with better performance in the Hayling task. We also present findings suggesting that individuals who perform well on tasks involving response inhibition, and WMC, also perform well on a speech-in-noise task. Our findings indicate that capacity to resist semantic interference can be used to predict performance on speech-in-noise tasks. © 2015 Scandinavian Psychological Associations and John Wiley & Sons Ltd.

Automated Assessment of Child Vocalization Development Using LENA.

PubMed

Richards, Jeffrey A; Xu, Dongxin; Gilkerson, Jill; Yapanel, Umit; Gray, Sharmistha; Paul, Terrance

2017-07-12

To produce a novel, efficient measure of children's expressive vocal development on the basis of automatic vocalization assessment (AVA), child vocalizations were automatically identified and extracted from audio recordings using Language Environment Analysis (LENA) System technology. Assessment was based on full-day audio recordings collected in a child's unrestricted, natural language environment. AVA estimates were derived using automatic speech recognition modeling techniques to categorize and quantify the sounds in child vocalizations (e.g., protophones and phonemes). These were expressed as phone and biphone frequencies, reduced to principal components, and inputted to age-based multiple linear regression models to predict independently collected criterion-expressive language scores. From these models, we generated vocal development AVA estimates as age-standardized scores and development age estimates. AVA estimates demonstrated strong statistical reliability and validity when compared with standard criterion expressive language assessments. Automated analysis of child vocalizations extracted from full-day recordings in natural settings offers a novel and efficient means to assess children's expressive vocal development. More research remains to identify specific mechanisms of operation.

Contribution of auditory working memory to speech understanding in mandarin-speaking cochlear implant users.

PubMed

Tao, Duoduo; Deng, Rui; Jiang, Ye; Galvin, John J; Fu, Qian-Jie; Chen, Bing

2014-01-01

To investigate how auditory working memory relates to speech perception performance by Mandarin-speaking cochlear implant (CI) users. Auditory working memory and speech perception was measured in Mandarin-speaking CI and normal-hearing (NH) participants. Working memory capacity was measured using forward digit span and backward digit span; working memory efficiency was measured using articulation rate. Speech perception was assessed with: (a) word-in-sentence recognition in quiet, (b) word-in-sentence recognition in speech-shaped steady noise at +5 dB signal-to-noise ratio, (c) Chinese disyllable recognition in quiet, (d) Chinese lexical tone recognition in quiet. Self-reported school rank was also collected regarding performance in schoolwork. There was large inter-subject variability in auditory working memory and speech performance for CI participants. Working memory and speech performance were significantly poorer for CI than for NH participants. All three working memory measures were strongly correlated with each other for both CI and NH participants. Partial correlation analyses were performed on the CI data while controlling for demographic variables. Working memory efficiency was significantly correlated only with sentence recognition in quiet when working memory capacity was partialled out. Working memory capacity was correlated with disyllable recognition and school rank when efficiency was partialled out. There was no correlation between working memory and lexical tone recognition in the present CI participants. Mandarin-speaking CI users experience significant deficits in auditory working memory and speech performance compared with NH listeners. The present data suggest that auditory working memory may contribute to CI users' difficulties in speech understanding. The present pattern of results with Mandarin-speaking CI users is consistent with previous auditory working memory studies with English-speaking CI users, suggesting that the lexical importance of voice pitch cues (albeit poorly coded by the CI) did not influence the relationship between working memory and speech perception.

Implementation of the Intelligent Voice System for Kazakh

NASA Astrophysics Data System (ADS)

Yessenbayev, Zh; Saparkhojayev, N.; Tibeyev, T.

2014-04-01

Modern speech technologies are highly advanced and widely used in day-to-day applications. However, this is mostly concerned with the languages of well-developed countries such as English, German, Japan, Russian, etc. As for Kazakh, the situation is less prominent and research in this field is only starting to evolve. In this research and application-oriented project, we introduce an intelligent voice system for the fast deployment of call-centers and information desks supporting Kazakh speech. The demand on such a system is obvious if the country's large size and small population is considered. The landline and cell phones become the only means of communication for the distant villages and suburbs. The system features Kazakh speech recognition and synthesis modules as well as a web-GUI for efficient dialog management. For speech recognition we use CMU Sphinx engine and for speech synthesis- MaryTTS. The web-GUI is implemented in Java enabling operators to quickly create and manage the dialogs in user-friendly graphical environment. The call routines are handled by Asterisk PBX and JBoss Application Server. The system supports such technologies and protocols as VoIP, VoiceXML, FastAGI, Java SpeechAPI and J2EE. For the speech recognition experiments we compiled and used the first Kazakh speech corpus with the utterances from 169 native speakers. The performance of the speech recognizer is 4.1% WER on isolated word recognition and 6.9% WER on clean continuous speech recognition tasks. The speech synthesis experiments include the training of male and female voices.

The NTID speech recognition test: NSRT(®).

PubMed

Bochner, Joseph H; Garrison, Wayne M; Doherty, Karen A

2015-07-01

The purpose of this study was to collect and analyse data necessary for expansion of the NSRT item pool and to evaluate the NSRT adaptive testing software. Participants were administered pure-tone and speech recognition tests including W-22 and QuickSIN, as well as a set of 323 new NSRT items and NSRT adaptive tests in quiet and background noise. Performance on the adaptive tests was compared to pure-tone thresholds and performance on other speech recognition measures. The 323 new items were subjected to Rasch scaling analysis. Seventy adults with mild to moderately severe hearing loss participated in this study. Their mean age was 62.4 years (sd = 20.8). The 323 new NSRT items fit very well with the original item bank, enabling the item pool to be more than doubled in size. Data indicate high reliability coefficients for the NSRT and moderate correlations with pure-tone thresholds (PTA and HFPTA) and other speech recognition measures (W-22, QuickSIN, and SRT). The adaptive NSRT is an efficient and effective measure of speech recognition, providing valid and reliable information concerning respondents' speech perception abilities.

Speech coding, reconstruction and recognition using acoustics and electromagnetic waves

DOE Office of Scientific and Technical Information (OSTI.GOV)

Holzrichter, J.F.; Ng, L.C.

The use of EM radiation in conjunction with simultaneously recorded acoustic speech information enables a complete mathematical coding of acoustic speech. The methods include the forming of a feature vector for each pitch period of voiced speech and the forming of feature vectors for each time frame of unvoiced, as well as for combined voiced and unvoiced speech. The methods include how to deconvolve the speech excitation function from the acoustic speech output to describe the transfer function each time frame. The formation of feature vectors defining all acoustic speech units over well defined time frames can be used formore » purposes of speech coding, speech compression, speaker identification, language-of-speech identification, speech recognition, speech synthesis, speech translation, speech telephony, and speech teaching. 35 figs.« less

Functional connectivity between face-movement and speech-intelligibility areas during auditory-only speech perception.

PubMed

Schall, Sonja; von Kriegstein, Katharina

2014-01-01

It has been proposed that internal simulation of the talking face of visually-known speakers facilitates auditory speech recognition. One prediction of this view is that brain areas involved in auditory-only speech comprehension interact with visual face-movement sensitive areas, even under auditory-only listening conditions. Here, we test this hypothesis using connectivity analyses of functional magnetic resonance imaging (fMRI) data. Participants (17 normal participants, 17 developmental prosopagnosics) first learned six speakers via brief voice-face or voice-occupation training (<2 min/speaker). This was followed by an auditory-only speech recognition task and a control task (voice recognition) involving the learned speakers' voices in the MRI scanner. As hypothesized, we found that, during speech recognition, familiarity with the speaker's face increased the functional connectivity between the face-movement sensitive posterior superior temporal sulcus (STS) and an anterior STS region that supports auditory speech intelligibility. There was no difference between normal participants and prosopagnosics. This was expected because previous findings have shown that both groups use the face-movement sensitive STS to optimize auditory-only speech comprehension. Overall, the present findings indicate that learned visual information is integrated into the analysis of auditory-only speech and that this integration results from the interaction of task-relevant face-movement and auditory speech-sensitive areas.

The impact of compression of speech signal, background noise and acoustic disturbances on the effectiveness of speaker identification

NASA Astrophysics Data System (ADS)

Kamiński, K.; Dobrowolski, A. P.

2017-04-01

The paper presents the architecture and the results of optimization of selected elements of the Automatic Speaker Recognition (ASR) system that uses Gaussian Mixture Models (GMM) in the classification process. Optimization was performed on the process of selection of individual characteristics using the genetic algorithm and the parameters of Gaussian distributions used to describe individual voices. The system that was developed was tested in order to evaluate the impact of different compression methods used, among others, in landline, mobile, and VoIP telephony systems, on effectiveness of the speaker identification. Also, the results were presented of effectiveness of speaker identification at specific levels of noise with the speech signal and occurrence of other disturbances that could appear during phone calls, which made it possible to specify the spectrum of applications of the presented ASR system.

Phonologic-graphemic transcodifier for Portuguese Language spoken in Brazil (PLB)

NASA Astrophysics Data System (ADS)

Fragadasilva, Francisco Jose; Saotome, Osamu; Deoliveira, Carlos Alberto

An automatic speech-to-text transformer system, suited to unlimited vocabulary, is presented. The basic acoustic unit considered are the allophones of the phonemes corresponding to the Portuguese language spoken in Brazil (PLB). The input to the system is a phonetic sequence, from a former step of isolated word recognition of slowly spoken speech. In a first stage, the system eliminates phonetic elements that don't belong to PLB. Using knowledge sources such as phonetics, phonology, orthography, and PLB specific lexicon, the output is a sequence of written words, ordered by probabilistic criterion that constitutes the set of graphemic possibilities to that input sequence. Pronunciation differences of some regions of Brazil are considered, but only those that cause differences in phonological transcription, because those of phonetic level are absorbed, during the transformation to phonological level. In the final stage, all possible written words are analyzed for orthography and grammar point of view, to eliminate the incorrect ones.

Recognition of Time-Compressed and Natural Speech with Selective Temporal Enhancements by Young and Elderly Listeners

ERIC Educational Resources Information Center

Gordon-Salant, Sandra; Fitzgibbons, Peter J.; Friedman, Sarah A.

2007-01-01

Purpose: The goal of this experiment was to determine whether selective slowing of speech segments improves recognition performance by young and elderly listeners. The hypotheses were (a) the benefits of time expansion occur for rapid speech but not for natural-rate speech, (b) selective time expansion of consonants produces greater score…

Automatic voice recognition using traditional and artificial neural network approaches

NASA Technical Reports Server (NTRS)

Botros, Nazeih M.

1989-01-01

The main objective of this research is to develop an algorithm for isolated-word recognition. This research is focused on digital signal analysis rather than linguistic analysis of speech. Features extraction is carried out by applying a Linear Predictive Coding (LPC) algorithm with order of 10. Continuous-word and speaker independent recognition will be considered in future study after accomplishing this isolated word research. To examine the similarity between the reference and the training sets, two approaches are explored. The first is implementing traditional pattern recognition techniques where a dynamic time warping algorithm is applied to align the two sets and calculate the probability of matching by measuring the Euclidean distance between the two sets. The second is implementing a backpropagation artificial neural net model with three layers as the pattern classifier. The adaptation rule implemented in this network is the generalized least mean square (LMS) rule. The first approach has been accomplished. A vocabulary of 50 words was selected and tested. The accuracy of the algorithm was found to be around 85 percent. The second approach is in progress at the present time.

Hierarchical singleton-type recurrent neural fuzzy networks for noisy speech recognition.

PubMed

Juang, Chia-Feng; Chiou, Chyi-Tian; Lai, Chun-Lung

2007-05-01

This paper proposes noisy speech recognition using hierarchical singleton-type recurrent neural fuzzy networks (HSRNFNs). The proposed HSRNFN is a hierarchical connection of two singleton-type recurrent neural fuzzy networks (SRNFNs), where one is used for noise filtering and the other for recognition. The SRNFN is constructed by recurrent fuzzy if-then rules with fuzzy singletons in the consequences, and their recurrent properties make them suitable for processing speech patterns with temporal characteristics. In n words recognition, n SRNFNs are created for modeling n words, where each SRNFN receives the current frame feature and predicts the next one of its modeling word. The prediction error of each SRNFN is used as recognition criterion. In filtering, one SRNFN is created, and each SRNFN recognizer is connected to the same SRNFN filter, which filters noisy speech patterns in the feature domain before feeding them to the SRNFN recognizer. Experiments with Mandarin word recognition under different types of noise are performed. Other recognizers, including multilayer perceptron (MLP), time-delay neural networks (TDNNs), and hidden Markov models (HMMs), are also tested and compared. These experiments and comparisons demonstrate good results with HSRNFN for noisy speech recognition tasks.

End-to-End ASR-Free Keyword Search From Speech

NASA Astrophysics Data System (ADS)

Audhkhasi, Kartik; Rosenberg, Andrew; Sethy, Abhinav; Ramabhadran, Bhuvana; Kingsbury, Brian

2017-12-01

End-to-end (E2E) systems have achieved competitive results compared to conventional hybrid hidden Markov model (HMM)-deep neural network based automatic speech recognition (ASR) systems. Such E2E systems are attractive due to the lack of dependence on alignments between input acoustic and output grapheme or HMM state sequence during training. This paper explores the design of an ASR-free end-to-end system for text query-based keyword search (KWS) from speech trained with minimal supervision. Our E2E KWS system consists of three sub-systems. The first sub-system is a recurrent neural network (RNN)-based acoustic auto-encoder trained to reconstruct the audio through a finite-dimensional representation. The second sub-system is a character-level RNN language model using embeddings learned from a convolutional neural network. Since the acoustic and text query embeddings occupy different representation spaces, they are input to a third feed-forward neural network that predicts whether the query occurs in the acoustic utterance or not. This E2E ASR-free KWS system performs respectably despite lacking a conventional ASR system and trains much faster.

Retrospective Analysis of Clinical Performance of an Estonian Speech Recognition System for Radiology: Effects of Different Acoustic and Language Models.

PubMed

Paats, A; Alumäe, T; Meister, E; Fridolin, I

2018-04-30

The aim of this study was to analyze retrospectively the influence of different acoustic and language models in order to determine the most important effects to the clinical performance of an Estonian language-based non-commercial radiology-oriented automatic speech recognition (ASR) system. An ASR system was developed for Estonian language in radiology domain by utilizing open-source software components (Kaldi toolkit, Thrax). The ASR system was trained with the real radiology text reports and dictations collected during development phases. The final version of the ASR system was tested by 11 radiologists who dictated 219 reports in total, in spontaneous manner in a real clinical environment. The audio files collected in the final phase were used to measure the performance of different versions of the ASR system retrospectively. ASR system versions were evaluated by word error rate (WER) for each speaker and modality and by WER difference for the first and the last version of the ASR system. Total average WER for the final version throughout all material was improved from 18.4% of the first version (v1) to 5.8% of the last (v8) version which corresponds to relative improvement of 68.5%. WER improvement was strongly related to modality and radiologist. In summary, the performance of the final ASR system version was close to optimal, delivering similar results to all modalities and being independent on user, the complexity of the radiology reports, user experience, and speech characteristics.

Deterioration of Speech Recognition Ability Over a Period of 5 Years in Adults Ages 18 to 70 Years: Results of the Dutch Online Speech-in-Noise Test.

PubMed

Stam, Mariska; Smits, Cas; Twisk, Jos W R; Lemke, Ulrike; Festen, Joost M; Kramer, Sophia E

2015-01-01

The first aim of the present study was to determine the change in speech recognition in noise over a period of 5 years in participants ages 18 to 70 years at baseline. The second aim was to investigate whether age, gender, educational level, the level of initial speech recognition in noise, and reported chronic conditions were associated with a change in speech recognition in noise. The baseline and 5-year follow-up data of 427 participants with and without hearing impairment participating in the National Longitudinal Study on Hearing (NL-SH) were analyzed. The ability to recognize speech in noise was measured twice with the online National Hearing Test, a digit-triplet speech-in-noise test. Speech-reception-threshold in noise (SRTn) scores were calculated, corresponding to 50% speech intelligibility. Unaided SRTn scores obtained with the same transducer (headphones or loudspeakers) at both test moments were included. Changes in SRTn were calculated as a raw shift (T1 - T0) and an adjusted shift for regression towards the mean. Paired t tests and multivariable linear regression analyses were applied. The mean increase (i.e., deterioration) in SRTn was 0.38-dB signal-to-noise ratio (SNR) over 5 years (p < 0.001). Results of the multivariable regression analyses showed that the age group of 50 to 59 years had a significantly larger deterioration in SRTn compared with the age group of 18 to 39 years (raw shift: beta: 0.64-dB SNR; 95% confidence interval: 0.07-1.22; p = 0.028, adjusted for initial speech recognition level - adjusted shift: beta: 0.82-dB SNR; 95% confidence interval: 0.27-1.34; p = 0.004). Gender, educational level, and the number of chronic conditions were not associated with a change in SRTn over time. No significant differences in increase of SRTn were found between the initial levels of speech recognition (i.e., good, insufficient, or poor) when taking into account the phenomenon regression towards the mean. The study results indicate that hearing deterioration of speech recognition in noise over 5 years can also be detected in adults ages 18 to 70 years. This rather small numeric change might represent a relevant impact on an individual's ability to understand speech in everyday life.

Enhancing speech recognition using improved particle swarm optimization based hidden Markov model.

PubMed

Selvaraj, Lokesh; Ganesan, Balakrishnan

2014-01-01

Enhancing speech recognition is the primary intention of this work. In this paper a novel speech recognition method based on vector quantization and improved particle swarm optimization (IPSO) is suggested. The suggested methodology contains four stages, namely, (i) denoising, (ii) feature mining (iii), vector quantization, and (iv) IPSO based hidden Markov model (HMM) technique (IP-HMM). At first, the speech signals are denoised using median filter. Next, characteristics such as peak, pitch spectrum, Mel frequency Cepstral coefficients (MFCC), mean, standard deviation, and minimum and maximum of the signal are extorted from the denoised signal. Following that, to accomplish the training process, the extracted characteristics are given to genetic algorithm based codebook generation in vector quantization. The initial populations are created by selecting random code vectors from the training set for the codebooks for the genetic algorithm process and IP-HMM helps in doing the recognition. At this point the creativeness will be done in terms of one of the genetic operation crossovers. The proposed speech recognition technique offers 97.14% accuracy.

Speaker recognition with temporal cues in acoustic and electric hearing

NASA Astrophysics Data System (ADS)

Vongphoe, Michael; Zeng, Fan-Gang

2005-08-01

Natural spoken language processing includes not only speech recognition but also identification of the speaker's gender, age, emotional, and social status. Our purpose in this study is to evaluate whether temporal cues are sufficient to support both speech and speaker recognition. Ten cochlear-implant and six normal-hearing subjects were presented with vowel tokens spoken by three men, three women, two boys, and two girls. In one condition, the subject was asked to recognize the vowel. In the other condition, the subject was asked to identify the speaker. Extensive training was provided for the speaker recognition task. Normal-hearing subjects achieved nearly perfect performance in both tasks. Cochlear-implant subjects achieved good performance in vowel recognition but poor performance in speaker recognition. The level of the cochlear implant performance was functionally equivalent to normal performance with eight spectral bands for vowel recognition but only to one band for speaker recognition. These results show a disassociation between speech and speaker recognition with primarily temporal cues, highlighting the limitation of current speech processing strategies in cochlear implants. Several methods, including explicit encoding of fundamental frequency and frequency modulation, are proposed to improve speaker recognition for current cochlear implant users.

Improving speech-in-noise recognition for children with hearing loss: Potential effects of language abilities, binaural summation, and head shadow

PubMed Central

Nittrouer, Susan; Caldwell-Tarr, Amanda; Tarr, Eric; Lowenstein, Joanna H.; Rice, Caitlin; Moberly, Aaron C.

2014-01-01

Objective: This study examined speech recognition in noise for children with hearing loss, compared it to recognition for children with normal hearing, and examined mechanisms that might explain variance in children’s abilities to recognize speech in noise. Design: Word recognition was measured in two levels of noise, both when the speech and noise were co-located in front and when the noise came separately from one side. Four mechanisms were examined as factors possibly explaining variance: vocabulary knowledge, sensitivity to phonological structure, binaural summation, and head shadow. Study sample: Participants were 113 eight-year-old children. Forty-eight had normal hearing (NH) and 65 had hearing loss: 18 with hearing aids (HAs), 19 with one cochlear implant (CI), and 28 with two CIs. Results: Phonological sensitivity explained a significant amount of between-groups variance in speech-in-noise recognition. Little evidence of binaural summation was found. Head shadow was similar in magnitude for children with NH and with CIs, regardless of whether they wore one or two CIs. Children with HAs showed reduced head shadow effects. Conclusion: These outcomes suggest that in order to improve speech-in-noise recognition for children with hearing loss, intervention needs to be comprehensive, focusing on both language abilities and auditory mechanisms. PMID:23834373

Auditory training of speech recognition with interrupted and continuous noise maskers by children with hearing impairment

PubMed Central

Sullivan, Jessica R.; Thibodeau, Linda M.; Assmann, Peter F.

2013-01-01

Previous studies have indicated that individuals with normal hearing (NH) experience a perceptual advantage for speech recognition in interrupted noise compared to continuous noise. In contrast, adults with hearing impairment (HI) and younger children with NH receive a minimal benefit. The objective of this investigation was to assess whether auditory training in interrupted noise would improve speech recognition in noise for children with HI and perhaps enhance their utilization of glimpsing skills. A partially-repeated measures design was used to evaluate the effectiveness of seven 1-h sessions of auditory training in interrupted and continuous noise. Speech recognition scores in interrupted and continuous noise were obtained from pre-, post-, and 3 months post-training from 24 children with moderate-to-severe hearing loss. Children who participated in auditory training in interrupted noise demonstrated a significantly greater improvement in speech recognition compared to those who trained in continuous noise. Those who trained in interrupted noise demonstrated similar improvements in both noise conditions while those who trained in continuous noise only showed modest improvements in the interrupted noise condition. This study presents direct evidence that auditory training in interrupted noise can be beneficial in improving speech recognition in noise for children with HI. PMID:23297921

The Relationship between Binaural Benefit and Difference in Unilateral Speech Recognition Performance for Bilateral Cochlear Implant Users

PubMed Central

Yoon, Yang-soo; Li, Yongxin; Kang, Hou-Yong; Fu, Qian-Jie

2011-01-01

Objective The full benefit of bilateral cochlear implants may depend on the unilateral performance with each device, the speech materials, processing ability of the user, and/or the listening environment. In this study, bilateral and unilateral speech performances were evaluated in terms of recognition of phonemes and sentences presented in quiet or in noise. Design Speech recognition was measured for unilateral left, unilateral right, and bilateral listening conditions; speech and noise were presented at 0° azimuth. The “binaural benefit” was defined as the difference between bilateral performance and unilateral performance with the better ear. Study Sample 9 adults with bilateral cochlear implants participated. Results On average, results showed a greater binaural benefit in noise than in quiet for all speech tests. More importantly, the binaural benefit was greater when unilateral performance was similar across ears. As the difference in unilateral performance between ears increased, the binaural advantage decreased; this functional relationship was observed across the different speech materials and noise levels even though there was substantial intra- and inter-subject variability. Conclusions The results indicate that subjects who show symmetry in speech recognition performance between implanted ears in general show a large binaural benefit. PMID:21696329

Investigation of an HMM/ANN hybrid structure in pattern recognition application using cepstral analysis of dysarthric (distorted) speech signals.

PubMed

Polur, Prasad D; Miller, Gerald E

2006-10-01

Computer speech recognition of individuals with dysarthria, such as cerebral palsy patients requires a robust technique that can handle conditions of very high variability and limited training data. In this study, application of a 10 state ergodic hidden Markov model (HMM)/artificial neural network (ANN) hybrid structure for a dysarthric speech (isolated word) recognition system, intended to act as an assistive tool, was investigated. A small size vocabulary spoken by three cerebral palsy subjects was chosen. The effect of such a structure on the recognition rate of the system was investigated by comparing it with an ergodic hidden Markov model as a control tool. This was done in order to determine if this modified technique contributed to enhanced recognition of dysarthric speech. The speech was sampled at 11 kHz. Mel frequency cepstral coefficients were extracted from them using 15 ms frames and served as training input to the hybrid model setup. The subsequent results demonstrated that the hybrid model structure was quite robust in its ability to handle the large variability and non-conformity of dysarthric speech. The level of variability in input dysarthric speech patterns sometimes limits the reliability of the system. However, its application as a rehabilitation/control tool to assist dysarthric motor impaired individuals holds sufficient promise.

Effects of intelligibility on working memory demand for speech perception.

PubMed

Francis, Alexander L; Nusbaum, Howard C

2009-08-01

Understanding low-intelligibility speech is effortful. In three experiments, we examined the effects of intelligibility on working memory (WM) demands imposed by perception of synthetic speech. In all three experiments, a primary speeded word recognition task was paired with a secondary WM-load task designed to vary the availability of WM capacity during speech perception. Speech intelligibility was varied either by training listeners to use available acoustic cues in a more diagnostic manner (as in Experiment 1) or by providing listeners with more informative acoustic cues (i.e., better speech quality, as in Experiments 2 and 3). In the first experiment, training significantly improved intelligibility and recognition speed; increasing WM load significantly slowed recognition. A significant interaction between training and load indicated that the benefit of training on recognition speed was observed only under low memory load. In subsequent experiments, listeners received no training; intelligibility was manipulated by changing synthesizers. Improving intelligibility without training improved recognition accuracy, and increasing memory load still decreased it, but more intelligible speech did not produce more efficient use of available WM capacity. This suggests that perceptual learning modifies the way available capacity is used, perhaps by increasing the use of more phonetically informative features and/or by decreasing use of less informative ones.

Self-Assessed Hearing Handicap in Older Adults With Poorer-Than-Predicted Speech Recognition in Noise.

PubMed

Eckert, Mark A; Matthews, Lois J; Dubno, Judy R

2017-01-01

Even older adults with relatively mild hearing loss report hearing handicap, suggesting that hearing handicap is not completely explained by reduced speech audibility. We examined the extent to which self-assessed ratings of hearing handicap using the Hearing Handicap Inventory for the Elderly (HHIE; Ventry & Weinstein, 1982) were significantly associated with measures of speech recognition in noise that controlled for differences in speech audibility. One hundred sixty-two middle-aged and older adults had HHIE total scores that were significantly associated with audibility-adjusted measures of speech recognition for low-context but not high-context sentences. These findings were driven by HHIE items involving negative feelings related to communication difficulties that also captured variance in subjective ratings of effort and frustration that predicted speech recognition. The average pure-tone threshold accounted for some of the variance in the association between the HHIE and audibility-adjusted speech recognition, suggesting an effect of central and peripheral auditory system decline related to elevated thresholds. The accumulation of difficult listening experiences appears to produce a self-assessment of hearing handicap resulting from (a) reduced audibility of stimuli, (b) declines in the central and peripheral auditory system function, and (c) additional individual variation in central nervous system function.

Self-Assessed Hearing Handicap in Older Adults With Poorer-Than-Predicted Speech Recognition in Noise

PubMed Central

Matthews, Lois J.; Dubno, Judy R.

2017-01-01

Purpose Even older adults with relatively mild hearing loss report hearing handicap, suggesting that hearing handicap is not completely explained by reduced speech audibility. Method We examined the extent to which self-assessed ratings of hearing handicap using the Hearing Handicap Inventory for the Elderly (HHIE; Ventry & Weinstein, 1982) were significantly associated with measures of speech recognition in noise that controlled for differences in speech audibility. Results One hundred sixty-two middle-aged and older adults had HHIE total scores that were significantly associated with audibility-adjusted measures of speech recognition for low-context but not high-context sentences. These findings were driven by HHIE items involving negative feelings related to communication difficulties that also captured variance in subjective ratings of effort and frustration that predicted speech recognition. The average pure-tone threshold accounted for some of the variance in the association between the HHIE and audibility-adjusted speech recognition, suggesting an effect of central and peripheral auditory system decline related to elevated thresholds. Conclusion The accumulation of difficult listening experiences appears to produce a self-assessment of hearing handicap resulting from (a) reduced audibility of stimuli, (b) declines in the central and peripheral auditory system function, and (c) additional individual variation in central nervous system function. PMID:28060993

Continuous multiword recognition performance of young and elderly listeners in ambient noise

NASA Astrophysics Data System (ADS)

Sato, Hiroshi

2005-09-01

Hearing threshold shift due to aging is known as a dominant factor to degrade speech recognition performance in noisy conditions. On the other hand, cognitive factors of aging-relating speech recognition performance in various speech-to-noise conditions are not well established. In this study, two kinds of speech test were performed to examine how working memory load relates to speech recognition performance. One is word recognition test with high-familiarity, four-syllable Japanese words (single-word test). In this test, each word was presented to listeners; the listeners were asked to write the word down on paper with enough time to answer. In the other test, five continuous word were presented to listeners and listeners were asked to write the word down after just five words were presented (multiword test). Both tests were done in various speech-to-noise ratios under 50-dBA Hoth spectrum noise with more than 50 young and elderly subjects. The results of two experiments suggest that (1) Hearing level is related to scores of both tests. (2) Scores of single-word test are well correlated with those of multiword test. (3) Scores of multiword test are not improved as speech-to-noise ratio improves in the condition where scores of single-word test reach their ceiling.

TRECVID: the utility of a content-based video retrieval evaluation

NASA Astrophysics Data System (ADS)

Hauptmann, Alexander G.

2006-01-01

TRECVID, an annual retrieval evaluation benchmark organized by NIST, encourages research in information retrieval from digital video. TRECVID benchmarking covers both interactive and manual searching by end users, as well as the benchmarking of some supporting technologies including shot boundary detection, extraction of semantic features, and the automatic segmentation of TV news broadcasts. Evaluations done in the context of the TRECVID benchmarks show that generally, speech transcripts and annotations provide the single most important clue for successful retrieval. However, automatically finding the individual images is still a tremendous and unsolved challenge. The evaluations repeatedly found that none of the multimedia analysis and retrieval techniques provide a significant benefit over retrieval using only textual information such as from automatic speech recognition transcripts or closed captions. In interactive systems, we do find significant differences among the top systems, indicating that interfaces can make a huge difference for effective video/image search. For interactive tasks efficient interfaces require few key clicks, but display large numbers of images for visual inspection by the user. The text search finds the right context region in the video in general, but to select specific relevant images we need good interfaces to easily browse the storyboard pictures. In general, TRECVID has motivated the video retrieval community to be honest about what we don't know how to do well (sometimes through painful failures), and has focused us to work on the actual task of video retrieval, as opposed to flashy demos based on technological capabilities.

Speech recognition: Acoustic phonetic and lexical knowledge representation

NASA Astrophysics Data System (ADS)

Zue, V. W.

1983-02-01

The purpose of this program is to develop a speech data base facility under which the acoustic characteristics of speech sounds in various contexts can be studied conveniently; investigate the phonological properties of a large lexicon of, say 10,000 words, and determine to what extent the phontactic constraints can be utilized in speech recognition; study the acoustic cues that are used to mark work boundaries; develop a test bed in the form of a large-vocabulary, IWR system to study the interactions of acoustic, phonetic and lexical knowledge; and develop a limited continuous speech recognition system with the goal of recognizing any English word from its spelling in order to assess the interactions of higher-level knowledge sources.

Microphone directionality, pre-emphasis filter, and wind noise in cochlear implants.

PubMed

Chung, King; McKibben, Nicholas

2011-10-01

Wind noise can be a nuisance or a debilitating masker for cochlear implant users in outdoor environments. Previous studies indicated that wind noise at the microphone/hearing aid output had high levels of low-frequency energy and the amount of noise generated is related to the microphone directionality. Currently, cochlear implants only offer either directional microphones or omnidirectional microphones for users at-large. As all cochlear implants utilize pre-emphasis filters to reduce low-frequency energy before the signal is encoded, effective wind noise reduction algorithms for hearing aids might not be applicable for cochlear implants. The purposes of this study were to investigate the effect of microphone directionality on speech recognition and perceived sound quality of cochlear implant users in wind noise and to derive effective wind noise reduction strategies for cochlear implants. A repeated-measure design was used to examine the effects of spectral and temporal masking created by wind noise recorded through directional and omnidirectional microphones and the effects of pre-emphasis filters on cochlear implant performance. A digital hearing aid was programmed to have linear amplification and relatively flat in-situ frequency responses for the directional and omnidirectional modes. The hearing aid output was then recorded from 0 to 360° at flow velocities of 4.5 and 13.5 m/sec in a quiet wind tunnel. Sixteen postlingually deafened adult cochlear implant listeners who reported to be able to communicate on the phone with friends and family without text messages participated in the study. Cochlear implant users listened to speech in wind noise recorded at locations that the directional and omnidirectional microphones yielded the lowest noise levels. Cochlear implant listeners repeated the sentences and rated the sound quality of the testing materials. Spectral and temporal characteristics of flow noise, as well as speech and/or noise characteristics before and after the pre-emphasis filter, were analyzed. Correlation coefficients between speech recognition scores and crest factors of wind noise before and after pre-emphasis filtering were also calculated. Listeners obtained higher scores using the omnidirectional than the directional microphone mode at 13.5 m/sec, but they obtained similar speech recognition scores for the two microphone modes at 4.5 m/sec. Higher correlation coefficients were obtained between speech recognition scores and crest factors of wind noise after pre-emphasis filtering rather than before filtering. Cochlear implant users would benefit from both directional and omnidirectional microphones to reduce far-field background noise and near-field wind noise. Automatic microphone switching algorithms can be more effective if the incoming signal were analyzed after pre-emphasis filters for microphone switching decisions. American Academy of Audiology.

Relationships among Rapid Digit Naming, Phonological Processing, Motor Automaticity, and Speech Perception in Poor, Average, and Good Readers and Spellers

ERIC Educational Resources Information Center

Savage, Robert S.; Frederickson, Norah; Goodwin, Roz; Patni, Ulla; Smith, Nicola; Tuersley, Louise

2005-01-01

In this article, we explore the relationship between rapid automatized naming (RAN) and other cognitive processes among below-average, average, and above-average readers and spellers. Nonsense word reading, phonological awareness, RAN, automaticity of balance, speech perception, and verbal short-term and working memory were measured. Factor…

Functional Connectivity between Face-Movement and Speech-Intelligibility Areas during Auditory-Only Speech Perception

PubMed Central

Schall, Sonja; von Kriegstein, Katharina

2014-01-01

It has been proposed that internal simulation of the talking face of visually-known speakers facilitates auditory speech recognition. One prediction of this view is that brain areas involved in auditory-only speech comprehension interact with visual face-movement sensitive areas, even under auditory-only listening conditions. Here, we test this hypothesis using connectivity analyses of functional magnetic resonance imaging (fMRI) data. Participants (17 normal participants, 17 developmental prosopagnosics) first learned six speakers via brief voice-face or voice-occupation training (<2 min/speaker). This was followed by an auditory-only speech recognition task and a control task (voice recognition) involving the learned speakers’ voices in the MRI scanner. As hypothesized, we found that, during speech recognition, familiarity with the speaker’s face increased the functional connectivity between the face-movement sensitive posterior superior temporal sulcus (STS) and an anterior STS region that supports auditory speech intelligibility. There was no difference between normal participants and prosopagnosics. This was expected because previous findings have shown that both groups use the face-movement sensitive STS to optimize auditory-only speech comprehension. Overall, the present findings indicate that learned visual information is integrated into the analysis of auditory-only speech and that this integration results from the interaction of task-relevant face-movement and auditory speech-sensitive areas. PMID:24466026

A preliminary comparison of speech recognition functionality in dental practice management systems.

PubMed

Irwin, Jeannie Y; Schleyer, Titus

2008-11-06

In this study, we examined speech recognition functionality in four leading dental practice management systems. Twenty dental students used voice to chart a simulated patient with 18 findings in each system. Results show it can take over a minute to chart one finding and that users frequently have to repeat commands. Limited functionality, poor usability and a high error rate appear to retard adoption of speech recognition in dentistry.

Two Stage Data Augmentation for Low Resourced Speech Recognition (Author’s Manuscript)

DTIC Science & Technology

2016-09-12

speech recognition, deep neural networks, data augmentation 1. Introduction When training data is limited—whether it be audio or text—the obvious...Schwartz, and S. Tsakalidis, “Enhancing low resource keyword spotting with au- tomatically retrieved web documents,” in Interspeech, 2015, pp. 839–843. [2...and F. Seide, “Feature learning in deep neural networks - a study on speech recognition tasks,” in International Conference on Learning Representations

Getting What You Want: Accurate Document Filtering in a Terabyte World

DTIC Science & Technology

2002-11-01

models are used widely in speech recognition and have shown promise for ad-hoc information retrieval (Ponte and Croft, 1998; Lafferty and Zhai, 2001...tasks is focused on developing techniques similar to those used in speech recognition. However the differing requirements of speech recognition and...Conference on Research and Development in Information Retrieval. ACM. 6. T.Ault, and Y. Yang. (2001.) kNN at TREC-9: A failure analysis. In

V2S: Voice to Sign Language Translation System for Malaysian Deaf People

NASA Astrophysics Data System (ADS)

Mean Foong, Oi; Low, Tang Jung; La, Wai Wan

The process of learning and understand the sign language may be cumbersome to some, and therefore, this paper proposes a solution to this problem by providing a voice (English Language) to sign language translation system using Speech and Image processing technique. Speech processing which includes Speech Recognition is the study of recognizing the words being spoken, regardless of whom the speaker is. This project uses template-based recognition as the main approach in which the V2S system first needs to be trained with speech pattern based on some generic spectral parameter set. These spectral parameter set will then be stored as template in a database. The system will perform the recognition process through matching the parameter set of the input speech with the stored templates to finally display the sign language in video format. Empirical results show that the system has 80.3% recognition rate.

Hemispheric lateralization of linguistic prosody recognition in comparison to speech and speaker recognition.

PubMed

Kreitewolf, Jens; Friederici, Angela D; von Kriegstein, Katharina

2014-11-15

Hemispheric specialization for linguistic prosody is a controversial issue. While it is commonly assumed that linguistic prosody and emotional prosody are preferentially processed in the right hemisphere, neuropsychological work directly comparing processes of linguistic prosody and emotional prosody suggests a predominant role of the left hemisphere for linguistic prosody processing. Here, we used two functional magnetic resonance imaging (fMRI) experiments to clarify the role of left and right hemispheres in the neural processing of linguistic prosody. In the first experiment, we sought to confirm previous findings showing that linguistic prosody processing compared to other speech-related processes predominantly involves the right hemisphere. Unlike previous studies, we controlled for stimulus influences by employing a prosody and speech task using the same speech material. The second experiment was designed to investigate whether a left-hemispheric involvement in linguistic prosody processing is specific to contrasts between linguistic prosody and emotional prosody or whether it also occurs when linguistic prosody is contrasted against other non-linguistic processes (i.e., speaker recognition). Prosody and speaker tasks were performed on the same stimulus material. In both experiments, linguistic prosody processing was associated with activity in temporal, frontal, parietal and cerebellar regions. Activation in temporo-frontal regions showed differential lateralization depending on whether the control task required recognition of speech or speaker: recognition of linguistic prosody predominantly involved right temporo-frontal areas when it was contrasted against speech recognition; when contrasted against speaker recognition, recognition of linguistic prosody predominantly involved left temporo-frontal areas. The results show that linguistic prosody processing involves functions of both hemispheres and suggest that recognition of linguistic prosody is based on an inter-hemispheric mechanism which exploits both a right-hemispheric sensitivity to pitch information and a left-hemispheric dominance in speech processing. Copyright © 2014 Elsevier Inc. All rights reserved.

Linguistic contributions to speech-on-speech masking for native and non-native listeners: language familiarity and semantic content.

PubMed

Brouwer, Susanne; Van Engen, Kristin J; Calandruccio, Lauren; Bradlow, Ann R

2012-02-01

This study examined whether speech-on-speech masking is sensitive to variation in the degree of similarity between the target and the masker speech. Three experiments investigated whether speech-in-speech recognition varies across different background speech languages (English vs Dutch) for both English and Dutch targets, as well as across variation in the semantic content of the background speech (meaningful vs semantically anomalous sentences), and across variation in listener status vis-à-vis the target and masker languages (native, non-native, or unfamiliar). The results showed that the more similar the target speech is to the masker speech (e.g., same vs different language, same vs different levels of semantic content), the greater the interference on speech recognition accuracy. Moreover, the listener's knowledge of the target and the background language modulate the size of the release from masking. These factors had an especially strong effect on masking effectiveness in highly unfavorable listening conditions. Overall this research provided evidence that that the degree of target-masker similarity plays a significant role in speech-in-speech recognition. The results also give insight into how listeners assign their resources differently depending on whether they are listening to their first or second language. © 2012 Acoustical Society of America

Linguistic contributions to speech-on-speech masking for native and non-native listeners: Language familiarity and semantic content

PubMed Central

Brouwer, Susanne; Van Engen, Kristin J.; Calandruccio, Lauren; Bradlow, Ann R.

2012-01-01

This study examined whether speech-on-speech masking is sensitive to variation in the degree of similarity between the target and the masker speech. Three experiments investigated whether speech-in-speech recognition varies across different background speech languages (English vs Dutch) for both English and Dutch targets, as well as across variation in the semantic content of the background speech (meaningful vs semantically anomalous sentences), and across variation in listener status vis-à-vis the target and masker languages (native, non-native, or unfamiliar). The results showed that the more similar the target speech is to the masker speech (e.g., same vs different language, same vs different levels of semantic content), the greater the interference on speech recognition accuracy. Moreover, the listener’s knowledge of the target and the background language modulate the size of the release from masking. These factors had an especially strong effect on masking effectiveness in highly unfavorable listening conditions. Overall this research provided evidence that that the degree of target-masker similarity plays a significant role in speech-in-speech recognition. The results also give insight into how listeners assign their resources differently depending on whether they are listening to their first or second language. PMID:22352516

Speech Recognition in Adults With Cochlear Implants: The Effects of Working Memory, Phonological Sensitivity, and Aging.

PubMed

Moberly, Aaron C; Harris, Michael S; Boyce, Lauren; Nittrouer, Susan

2017-04-14

Models of speech recognition suggest that "top-down" linguistic and cognitive functions, such as use of phonotactic constraints and working memory, facilitate recognition under conditions of degradation, such as in noise. The question addressed in this study was what happens to these functions when a listener who has experienced years of hearing loss obtains a cochlear implant. Thirty adults with cochlear implants and 30 age-matched controls with age-normal hearing underwent testing of verbal working memory using digit span and serial recall of words. Phonological capacities were assessed using a lexical decision task and nonword repetition. Recognition of words in sentences in speech-shaped noise was measured. Implant users had only slightly poorer working memory accuracy than did controls and only on serial recall of words; however, phonological sensitivity was highly impaired. Working memory did not facilitate speech recognition in noise for either group. Phonological sensitivity predicted sentence recognition for implant users but not for listeners with normal hearing. Clinical speech recognition outcomes for adult implant users relate to the ability of these users to process phonological information. Results suggest that phonological capacities may serve as potential clinical targets through rehabilitative training. Such novel interventions may be particularly helpful for older adult implant users.

Speech Recognition in Adults With Cochlear Implants: The Effects of Working Memory, Phonological Sensitivity, and Aging

PubMed Central

Harris, Michael S.; Boyce, Lauren; Nittrouer, Susan

2017-01-01

Purpose Models of speech recognition suggest that “top-down” linguistic and cognitive functions, such as use of phonotactic constraints and working memory, facilitate recognition under conditions of degradation, such as in noise. The question addressed in this study was what happens to these functions when a listener who has experienced years of hearing loss obtains a cochlear implant. Method Thirty adults with cochlear implants and 30 age-matched controls with age-normal hearing underwent testing of verbal working memory using digit span and serial recall of words. Phonological capacities were assessed using a lexical decision task and nonword repetition. Recognition of words in sentences in speech-shaped noise was measured. Results Implant users had only slightly poorer working memory accuracy than did controls and only on serial recall of words; however, phonological sensitivity was highly impaired. Working memory did not facilitate speech recognition in noise for either group. Phonological sensitivity predicted sentence recognition for implant users but not for listeners with normal hearing. Conclusion Clinical speech recognition outcomes for adult implant users relate to the ability of these users to process phonological information. Results suggest that phonological capacities may serve as potential clinical targets through rehabilitative training. Such novel interventions may be particularly helpful for older adult implant users. PMID:28384805

Effects of Semantic Context and Fundamental Frequency Contours on Mandarin Speech Recognition by Second Language Learners.

PubMed

Zhang, Linjun; Li, Yu; Wu, Han; Li, Xin; Shu, Hua; Zhang, Yang; Li, Ping

2016-01-01

Speech recognition by second language (L2) learners in optimal and suboptimal conditions has been examined extensively with English as the target language in most previous studies. This study extended existing experimental protocols (Wang et al., 2013) to investigate Mandarin speech recognition by Japanese learners of Mandarin at two different levels (elementary vs. intermediate) of proficiency. The overall results showed that in addition to L2 proficiency, semantic context, F0 contours, and listening condition all affected the recognition performance on the Mandarin sentences. However, the effects of semantic context and F0 contours on L2 speech recognition diverged to some extent. Specifically, there was significant modulation effect of listening condition on semantic context, indicating that L2 learners made use of semantic context less efficiently in the interfering background than in quiet. In contrast, no significant modulation effect of listening condition on F0 contours was found. Furthermore, there was significant interaction between semantic context and F0 contours, indicating that semantic context becomes more important for L2 speech recognition when F0 information is degraded. None of these effects were found to be modulated by L2 proficiency. The discrepancy in the effects of semantic context and F0 contours on L2 speech recognition in the interfering background might be related to differences in processing capacities required by the two types of information in adverse listening conditions.

Speech Recognition Thresholds for Multilingual Populations.

ERIC Educational Resources Information Center

Ramkissoon, Ishara

2001-01-01

This article traces the development of speech audiometry in the United States and reports on the current status, focusing on the needs of a multilingual population in terms of measuring speech recognition threshold (SRT). It also discusses sociolinguistic considerations, alternative SRT stimuli for second language learners, and research on using…

A physiologically-inspired model reproducing the speech intelligibility benefit in cochlear implant listeners with residual acoustic hearing.

PubMed

Zamaninezhad, Ladan; Hohmann, Volker; Büchner, Andreas; Schädler, Marc René; Jürgens, Tim

2017-02-01

This study introduces a speech intelligibility model for cochlear implant users with ipsilateral preserved acoustic hearing that aims at simulating the observed speech-in-noise intelligibility benefit when receiving simultaneous electric and acoustic stimulation (EA-benefit). The model simulates the auditory nerve spiking in response to electric and/or acoustic stimulation. The temporally and spatially integrated spiking patterns were used as the final internal representation of noisy speech. Speech reception thresholds (SRTs) in stationary noise were predicted for a sentence test using an automatic speech recognition framework. The model was employed to systematically investigate the effect of three physiologically relevant model factors on simulated SRTs: (1) the spatial spread of the electric field which co-varies with the number of electrically stimulated auditory nerves, (2) the "internal" noise simulating the deprivation of auditory system, and (3) the upper bound frequency limit of acoustic hearing. The model results show that the simulated SRTs increase monotonically with increasing spatial spread for fixed internal noise, and also increase with increasing the internal noise strength for a fixed spatial spread. The predicted EA-benefit does not follow such a systematic trend and depends on the specific combination of the model parameters. Beyond 300 Hz, the upper bound limit for preserved acoustic hearing is less influential on speech intelligibility of EA-listeners in stationary noise. The proposed model-predicted EA-benefits are within the range of EA-benefits shown by 18 out of 21 actual cochlear implant listeners with preserved acoustic hearing. Copyright © 2016 Elsevier B.V. All rights reserved.

Investigation of potential cognitive tests for use with older adults in audiology clinics.

PubMed

Vaughan, Nancy; Storzbach, Daniel; Furukawa, Izumi

2008-01-01

Cognitive declines in working memory and processing speed are hallmarks of aging. Deficits in speech understanding also are seen in aging individuals. A clinical test to determine whether the cognitive aging changes contribute to aging speech understanding difficulties would be helpful for determining rehabilitation strategies in audiology clinics. To identify a clinical neurocognitive test or battery of tests that could be used in audiology clinics to help explain deficits in speech recognition in some older listeners. A correlational study examining the association between certain cognitive test scores and speech recognition performance. Speeded (time-compressed) speech was used to increase the cognitive processing load. Two hundred twenty-five adults aged 50 through 75 years were participants in this study. Both batteries of tests were administered to all participants in two separate sessions. A selected battery of neurocognitive tests and a time-compressed speech recognition test battery using various rates of speech were administered. Principal component analysis was used to extract the important component factors from each set of tests, and regression models were constructed to examine the association between tests and to identify the neurocognitive test most strongly associated with speech recognition performance. A sequencing working memory test (Letter-Number Sequencing [LNS]) was most strongly associated with rapid speech understanding. The association between the LNS test results and the compressed sentence recognition scores (CSRS) was strong even when age and hearing loss were controlled. The LNS is a sequencing test that provides information about temporal processing at the cognitive level and may prove useful in diagnosis of speech understanding problems, and in the development of aural rehabilitation and training strategies.

Recognition of voice commands using adaptation of foreign language speech recognizer via selection of phonetic transcriptions

NASA Astrophysics Data System (ADS)

Maskeliunas, Rytis; Rudzionis, Vytautas

2011-06-01

In recent years various commercial speech recognizers have become available. These recognizers provide the possibility to develop applications incorporating various speech recognition techniques easily and quickly. All of these commercial recognizers are typically targeted to widely spoken languages having large market potential; however, it may be possible to adapt available commercial recognizers for use in environments where less widely spoken languages are used. Since most commercial recognition engines are closed systems the single avenue for the adaptation is to try set ways for the selection of proper phonetic transcription methods between the two languages. This paper deals with the methods to find the phonetic transcriptions for Lithuanian voice commands to be recognized using English speech engines. The experimental evaluation showed that it is possible to find phonetic transcriptions that will enable the recognition of Lithuanian voice commands with recognition accuracy of over 90%.

Time-Warp–Invariant Neuronal Processing

PubMed Central

Gütig, Robert; Sompolinsky, Haim

2009-01-01

Fluctuations in the temporal durations of sensory signals constitute a major source of variability within natural stimulus ensembles. The neuronal mechanisms through which sensory systems can stabilize perception against such fluctuations are largely unknown. An intriguing instantiation of such robustness occurs in human speech perception, which relies critically on temporal acoustic cues that are embedded in signals with highly variable duration. Across different instances of natural speech, auditory cues can undergo temporal warping that ranges from 2-fold compression to 2-fold dilation without significant perceptual impairment. Here, we report that time-warp–invariant neuronal processing can be subserved by the shunting action of synaptic conductances that automatically rescales the effective integration time of postsynaptic neurons. We propose a novel spike-based learning rule for synaptic conductances that adjusts the degree of synaptic shunting to the temporal processing requirements of a given task. Applying this general biophysical mechanism to the example of speech processing, we propose a neuronal network model for time-warp–invariant word discrimination and demonstrate its excellent performance on a standard benchmark speech-recognition task. Our results demonstrate the important functional role of synaptic conductances in spike-based neuronal information processing and learning. The biophysics of temporal integration at neuronal membranes can endow sensory pathways with powerful time-warp–invariant computational capabilities. PMID:19582146

Speech Recognition for Medical Dictation: Overview in Quebec and Systematic Review.

PubMed

Poder, Thomas G; Fisette, Jean-François; Déry, Véronique

2018-04-03

Speech recognition is increasingly used in medical reporting. The aim of this article is to identify in the literature the strengths and weaknesses of this technology, as well as barriers to and facilitators of its implementation. A systematic review of systematic reviews was performed using PubMed, Scopus, the Cochrane Library and the Center for Reviews and Dissemination through August 2017. The gray literature has also been consulted. The quality of systematic reviews has been assessed with the AMSTAR checklist. The main inclusion criterion was use of speech recognition for medical reporting (front-end or back-end). A survey has also been conducted in Quebec, Canada, to identify the dissemination of this technology in this province, as well as the factors leading to the success or failure of its implementation. Five systematic reviews were identified. These reviews indicated a high level of heterogeneity across studies. The quality of the studies reported was generally poor. Speech recognition is not as accurate as human transcription, but it can dramatically reduce turnaround times for reporting. In front-end use, medical doctors need to spend more time on dictation and correction than required with human transcription. With speech recognition, major errors occur up to three times more frequently. In back-end use, a potential increase in productivity of transcriptionists was noted. In conclusion, speech recognition offers several advantages for medical reporting. However, these advantages are countered by an increased burden on medical doctors and by risks of additional errors in medical reports. It is also hard to identify for which medical specialties and which clinical activities the use of speech recognition will be the most beneficial.

Differences in Speech Recognition Between Children with Attention Deficits and Typically Developed Children Disappear When Exposed to 65 dB of Auditory Noise

PubMed Central

Söderlund, Göran B. W.; Jobs, Elisabeth Nilsson

2016-01-01

The most common neuropsychiatric condition in the in children is attention deficit hyperactivity disorder (ADHD), affecting ∼6–9% of the population. ADHD is distinguished by inattention and hyperactive, impulsive behaviors as well as poor performance in various cognitive tasks often leading to failures at school. Sensory and perceptual dysfunctions have also been noticed. Prior research has mainly focused on limitations in executive functioning where differences are often explained by deficits in pre-frontal cortex activation. Less notice has been given to sensory perception and subcortical functioning in ADHD. Recent research has shown that children with ADHD diagnosis have a deviant auditory brain stem response compared to healthy controls. The aim of the present study was to investigate if the speech recognition threshold differs between attentive and children with ADHD symptoms in two environmental sound conditions, with and without external noise. Previous research has namely shown that children with attention deficits can benefit from white noise exposure during cognitive tasks and here we investigate if noise benefit is present during an auditory perceptual task. For this purpose we used a modified Hagerman’s speech recognition test where children with and without attention deficits performed a binaural speech recognition task to assess the speech recognition threshold in no noise and noise conditions (65 dB). Results showed that the inattentive group displayed a higher speech recognition threshold than typically developed children and that the difference in speech recognition threshold disappeared when exposed to noise at supra threshold level. From this we conclude that inattention can partly be explained by sensory perceptual limitations that can possibly be ameliorated through noise exposure. PMID:26858679

Age and measurement time-of-day effects on speech recognition in noise.

PubMed

Veneman, Carrie E; Gordon-Salant, Sandra; Matthews, Lois J; Dubno, Judy R

2013-01-01

The purpose of this study was to determine the effect of measurement time of day on speech recognition in noise and the extent to which time-of-day effects differ with age. Older adults tend to have more difficulty understanding speech in noise than younger adults, even when hearing is normal. Two possible contributors to this age difference in speech recognition may be measurement time of day and inhibition. Most younger adults are "evening-type," showing peak circadian arousal in the evening, whereas most older adults are "morning-type," with circadian arousal peaking in the morning. Tasks that require inhibition of irrelevant information have been shown to be affected by measurement time of day, with maximum performance attained at one's peak time of day. The authors hypothesized that a change in inhibition will be associated with measurement time of day and therefore affect speech recognition in noise, with better performance in the morning for older adults and in the evening for younger adults. Fifteen younger evening-type adults (20-28 years) and 15 older morning-type adults with normal hearing (66-78 years) listened to the Hearing in Noise Test (HINT) and the Quick Speech in Noise (QuickSIN) test in the morning and evening (peak and off-peak times). Time of day preference was assessed using the Morningness-Eveningness Questionnaire. Sentences and noise were presented binaurally through insert earphones. During morning and evening sessions, participants solved word-association problems within the visual-distraction task (VDT), which was used as an estimate of inhibition. After each session, participants rated perceived mental demand of the tasks using a revised version of the NASA Task Load Index. Younger adults performed significantly better on the speech-in-noise tasks and rated themselves as requiring significantly less mental demand when tested at their peak (evening) than off-peak (morning) time of day. In contrast, time-of-day effects were not observed for the older adults on the speech recognition or rating tasks. Although older adults required significantly more advantageous signal-to-noise ratios than younger adults for equivalent speech-recognition performance, a significantly larger younger versus older age difference in speech recognition was observed in the evening than in the morning. Older adults performed significantly poorer than younger adults on the VDT, but performance was not affected by measurement time of day. VDT performance for misleading distracter items was significantly correlated with HINT and QuickSIN test performance at the peak measurement time of day. Although all participants had normal hearing, speech recognition in noise was significantly poorer for older than younger adults, with larger age-related differences in the evening (an off-peak time for older adults) than in the morning. The significant effect of measurement time of day suggests that this factor may impact the clinical assessment of speech recognition in noise for all individuals. It appears that inhibition, as estimated by a visual distraction task for misleading visual items, is a cognitive mechanism that is related to speech-recognition performance in noise, at least at a listener's peak time of day.

Accelerometer-based automatic voice onset detection in speech mapping with navigated repetitive transcranial magnetic stimulation.

PubMed

Vitikainen, Anne-Mari; Mäkelä, Elina; Lioumis, Pantelis; Jousmäki, Veikko; Mäkelä, Jyrki P

2015-09-30

The use of navigated repetitive transcranial magnetic stimulation (rTMS) in mapping of speech-related brain areas has recently shown to be useful in preoperative workflow of epilepsy and tumor patients. However, substantial inter- and intraobserver variability and non-optimal replicability of the rTMS results have been reported, and a need for additional development of the methodology is recognized. In TMS motor cortex mappings the evoked responses can be quantitatively monitored by electromyographic recordings; however, no such easily available setup exists for speech mappings. We present an accelerometer-based setup for detection of vocalization-related larynx vibrations combined with an automatic routine for voice onset detection for rTMS speech mapping applying naming. The results produced by the automatic routine were compared with the manually reviewed video-recordings. The new method was applied in the routine navigated rTMS speech mapping for 12 consecutive patients during preoperative workup for epilepsy or tumor surgery. The automatic routine correctly detected 96% of the voice onsets, resulting in 96% sensitivity and 71% specificity. Majority (63%) of the misdetections were related to visible throat movements, extra voices before the response, or delayed naming of the previous stimuli. The no-response errors were correctly detected in 88% of events. The proposed setup for automatic detection of voice onsets provides quantitative additional data for analysis of the rTMS-induced speech response modifications. The objectively defined speech response latencies increase the repeatability, reliability and stratification of the rTMS results. Copyright © 2015 Elsevier B.V. All rights reserved.

Multitasking During Degraded Speech Recognition in School-Age Children

PubMed Central

Ward, Kristina M.; Brehm, Laurel

2017-01-01

Multitasking requires individuals to allocate their cognitive resources across different tasks. The purpose of the current study was to assess school-age children’s multitasking abilities during degraded speech recognition. Children (8 to 12 years old) completed a dual-task paradigm including a sentence recognition (primary) task containing speech that was either unprocessed or noise-band vocoded with 8, 6, or 4 spectral channels and a visual monitoring (secondary) task. Children’s accuracy and reaction time on the visual monitoring task was quantified during the dual-task paradigm in each condition of the primary task and compared with single-task performance. Children experienced dual-task costs in the 6- and 4-channel conditions of the primary speech recognition task with decreased accuracy on the visual monitoring task relative to baseline performance. In all conditions, children’s dual-task performance on the visual monitoring task was strongly predicted by their single-task (baseline) performance on the task. Results suggest that children’s proficiency with the secondary task contributes to the magnitude of dual-task costs while multitasking during degraded speech recognition. PMID:28105890

Multitasking During Degraded Speech Recognition in School-Age Children.

PubMed

Grieco-Calub, Tina M; Ward, Kristina M; Brehm, Laurel

2017-01-01

Multitasking requires individuals to allocate their cognitive resources across different tasks. The purpose of the current study was to assess school-age children's multitasking abilities during degraded speech recognition. Children (8 to 12 years old) completed a dual-task paradigm including a sentence recognition (primary) task containing speech that was either unprocessed or noise-band vocoded with 8, 6, or 4 spectral channels and a visual monitoring (secondary) task. Children's accuracy and reaction time on the visual monitoring task was quantified during the dual-task paradigm in each condition of the primary task and compared with single-task performance. Children experienced dual-task costs in the 6- and 4-channel conditions of the primary speech recognition task with decreased accuracy on the visual monitoring task relative to baseline performance. In all conditions, children's dual-task performance on the visual monitoring task was strongly predicted by their single-task (baseline) performance on the task. Results suggest that children's proficiency with the secondary task contributes to the magnitude of dual-task costs while multitasking during degraded speech recognition.

Processing Electromyographic Signals to Recognize Words

NASA Technical Reports Server (NTRS)

Jorgensen, C. C.; Lee, D. D.

2009-01-01

A recently invented speech-recognition method applies to words that are articulated by means of the tongue and throat muscles but are otherwise not voiced or, at most, are spoken sotto voce. This method could satisfy a need for speech recognition under circumstances in which normal audible speech is difficult, poses a hazard, is disturbing to listeners, or compromises privacy. The method could also be used to augment traditional speech recognition by providing an additional source of information about articulator activity. The method can be characterized as intermediate between (1) conventional speech recognition through processing of voice sounds and (2) a method, not yet developed, of processing electroencephalographic signals to extract unspoken words directly from thoughts. This method involves computational processing of digitized electromyographic (EMG) signals from muscle innervation acquired by surface electrodes under a subject's chin near the tongue and on the side of the subject s throat near the larynx. After preprocessing, digitization, and feature extraction, EMG signals are processed by a neural-network pattern classifier, implemented in software, that performs the bulk of the recognition task as described.

How Does Reading Performance Modulate the Impact of Orthographic Knowledge on Speech Processing? A Comparison of Normal Readers and Dyslexic Adults

ERIC Educational Resources Information Center

Pattamadilok, Chotiga; Nelis, Aubéline; Kolinsky, Régine

2014-01-01

Studies on proficient readers showed that speech processing is affected by knowledge of the orthographic code. Yet, the automaticity of the orthographic influence depends on task demand. Here, we addressed this automaticity issue in normal and dyslexic adult readers by comparing the orthographic effects obtained in two speech processing tasks that…

Relations Between Self-reported Executive Functioning and Speech Perception Skills in Adult Cochlear Implant Users.

PubMed

Moberly, Aaron C; Patel, Tirth R; Castellanos, Irina

2018-02-01

As a result of their hearing loss, adults with cochlear implants (CIs) would self-report poorer executive functioning (EF) skills than normal-hearing (NH) peers, and these EF skills would be associated with performance on speech recognition tasks. EF refers to a group of high order neurocognitive skills responsible for behavioral and emotional regulation during goal-directed activity, and EF has been found to be poorer in children with CIs than their NH age-matched peers. Moreover, there is increasing evidence that neurocognitive skills, including some EF skills, contribute to the ability to recognize speech through a CI. Thirty postlingually deafened adults with CIs and 42 age-matched NH adults were enrolled. Participants and their spouses or significant others (informants) completed well-validated self-reports or informant-reports of EF, the Behavior Rating Inventory of Executive Function - Adult (BRIEF-A). CI users' speech recognition skills were assessed in quiet using several measures of sentence recognition. NH peers were tested for recognition of noise-vocoded versions of the same speech stimuli. CI users self-reported difficulty on EF tasks of shifting and task monitoring. In CI users, measures of speech recognition correlated with several self-reported EF skills. The present findings provide further evidence that neurocognitive factors, including specific EF skills, may decline in association with hearing loss, and that some of these EF skills contribute to speech processing under degraded listening conditions.

Spontaneous Speech Collection for the CSR Corpus

DTIC Science & Technology

1992-01-01

Menlo Park, California 94025 1. ABSTRACT As part of a pilot data collection for DARPA’s Continuous Speech Recognition ( CSR ) speech corpus, SRI...International experi- mented with the collection of spontaneous speeoh material. The bulk of the CSR pilot data was read versions of news articles from...variable. 2. INTRODUCTION The CSR (Continuous Speech Recognition) Corpus collec- tion can be considered the successor to the Resource Man- agemen t

Eyes and ears: Using eye tracking and pupillometry to understand challenges to speech recognition.

PubMed

Van Engen, Kristin J; McLaughlin, Drew J

2018-05-04

Although human speech recognition is often experienced as relatively effortless, a number of common challenges can render the task more difficult. Such challenges may originate in talkers (e.g., unfamiliar accents, varying speech styles), the environment (e.g. noise), or in listeners themselves (e.g., hearing loss, aging, different native language backgrounds). Each of these challenges can reduce the intelligibility of spoken language, but even when intelligibility remains high, they can place greater processing demands on listeners. Noisy conditions, for example, can lead to poorer recall for speech, even when it has been correctly understood. Speech intelligibility measures, memory tasks, and subjective reports of listener difficulty all provide critical information about the effects of such challenges on speech recognition. Eye tracking and pupillometry complement these methods by providing objective physiological measures of online cognitive processing during listening. Eye tracking records the moment-to-moment direction of listeners' visual attention, which is closely time-locked to unfolding speech signals, and pupillometry measures the moment-to-moment size of listeners' pupils, which dilate in response to increased cognitive load. In this paper, we review the uses of these two methods for studying challenges to speech recognition. Copyright © 2018. Published by Elsevier B.V.

Robust recognition of loud and Lombard speech in the fighter cockpit environment

NASA Astrophysics Data System (ADS)

Stanton, Bill J., Jr.

1988-08-01

There are a number of challenges associated with incorporating speech recognition technology into the fighter cockpit. One of the major problems is the wide range of variability in the pilot's voice. That can result from changing levels of stress and workload. Increasing the training set to include abnormal speech is not an attractive option because of the innumerable conditions that would have to be represented and the inordinate amount of time to collect such a training set. A more promising approach is to study subsets of abnormal speech that have been produced under controlled cockpit conditions with the purpose of characterizing reliable shifts that occur relative to normal speech. Such was the initiative of this research. Analyses were conducted for 18 features on 17671 phoneme tokens across eight speakers for normal, loud, and Lombard speech. It was discovered that there was a consistent migration of energy in the sonorants. This discovery of reliable energy shifts led to the development of a method to reduce or eliminate these shifts in the Euclidean distances between LPC log magnitude spectra. This combination significantly improved recognition performance of loud and Lombard speech. Discrepancies in recognition error rates between normal and abnormal speech were reduced by approximately 50 percent for all eight speakers combined.

Robust relationship between reading span and speech recognition in noise

PubMed Central

Souza, Pamela; Arehart, Kathryn

2015-01-01

Objective Working memory refers to a cognitive system that manages information processing and temporary storage. Recent work has demonstrated that individual differences in working memory capacity measured using a reading span task are related to ability to recognize speech in noise. In this project, we investigated whether the specific implementation of the reading span task influenced the strength of the relationship between working memory capacity and speech recognition. Design The relationship between speech recognition and working memory capacity was examined for two different working memory tests that varied in approach, using a within-subject design. Data consisted of audiometric results along with the two different working memory tests; one speech-in-noise test; and a reading comprehension test. Study sample The test group included 94 older adults with varying hearing loss and 30 younger adults with normal hearing. Results Listeners with poorer working memory capacity had more difficulty understanding speech in noise after accounting for age and degree of hearing loss. That relationship did not differ significantly between the two different implementations of reading span. Conclusions Our findings suggest that different implementations of a verbal reading span task do not affect the strength of the relationship between working memory capacity and speech recognition. PMID:25975360

Robust relationship between reading span and speech recognition in noise.

PubMed

Souza, Pamela; Arehart, Kathryn

2015-01-01

Working memory refers to a cognitive system that manages information processing and temporary storage. Recent work has demonstrated that individual differences in working memory capacity measured using a reading span task are related to ability to recognize speech in noise. In this project, we investigated whether the specific implementation of the reading span task influenced the strength of the relationship between working memory capacity and speech recognition. The relationship between speech recognition and working memory capacity was examined for two different working memory tests that varied in approach, using a within-subject design. Data consisted of audiometric results along with the two different working memory tests; one speech-in-noise test; and a reading comprehension test. The test group included 94 older adults with varying hearing loss and 30 younger adults with normal hearing. Listeners with poorer working memory capacity had more difficulty understanding speech in noise after accounting for age and degree of hearing loss. That relationship did not differ significantly between the two different implementations of reading span. Our findings suggest that different implementations of a verbal reading span task do not affect the strength of the relationship between working memory capacity and speech recognition.

[Perception of emotional intonation of noisy speech signal with different acoustic parameters by adults of different age and gender].

PubMed

Dmitrieva, E S; Gel'man, V Ia

2011-01-01

The listener-distinctive features of recognition of different emotional intonations (positive, negative and neutral) of male and female speakers in the presence or absence of background noise were studied in 49 adults aged 20-79 years. In all the listeners noise produced the most pronounced decrease in recognition accuracy for positive emotional intonation ("joy") as compared to other intonations, whereas it did not influence the recognition accuracy of "anger" in 65-79-year-old listeners. The higher emotion recognition rates of a noisy signal were observed for speech emotional intonations expressed by female speakers. Acoustic characteristics of noisy and clear speech signals underlying perception of speech emotional prosody were found for adult listeners of different age and gender.

Evaluating deep learning architectures for Speech Emotion Recognition.

PubMed

Fayek, Haytham M; Lech, Margaret; Cavedon, Lawrence

2017-08-01

Speech Emotion Recognition (SER) can be regarded as a static or dynamic classification problem, which makes SER an excellent test bed for investigating and comparing various deep learning architectures. We describe a frame-based formulation to SER that relies on minimal speech processing and end-to-end deep learning to model intra-utterance dynamics. We use the proposed SER system to empirically explore feed-forward and recurrent neural network architectures and their variants. Experiments conducted illuminate the advantages and limitations of these architectures in paralinguistic speech recognition and emotion recognition in particular. As a result of our exploration, we report state-of-the-art results on the IEMOCAP database for speaker-independent SER and present quantitative and qualitative assessments of the models' performances. Copyright © 2017 Elsevier Ltd. All rights reserved.

Vocal Tract Representation in the Recognition of Cerebral Palsied Speech

ERIC Educational Resources Information Center

Rudzicz, Frank; Hirst, Graeme; van Lieshout, Pascal

2012-01-01

Purpose: In this study, the authors explored articulatory information as a means of improving the recognition of dysarthric speech by machine. Method: Data were derived chiefly from the TORGO database of dysarthric articulation (Rudzicz, Namasivayam, & Wolff, 2011) in which motions of various points in the vocal tract are measured during speech.…

Micro-Based Speech Recognition: Instructional Innovation for Handicapped Learners.

ERIC Educational Resources Information Center

Horn, Carin E.; Scott, Brian L.

A new voice based learning system (VBLS), which allows the handicapped user to interact with a microcomputer by voice commands, is described. Speech or voice recognition is the computerized process of identifying a spoken word or phrase, including those resulting from speech impediments. This new technology is helpful to the severely physically…

Automatic detection of swallowing events by acoustical means for applications of monitoring of ingestive behavior.

PubMed

Sazonov, Edward S; Makeyev, Oleksandr; Schuckers, Stephanie; Lopez-Meyer, Paulo; Melanson, Edward L; Neuman, Michael R

2010-03-01

Our understanding of etiology of obesity and overweight is incomplete due to lack of objective and accurate methods for monitoring of ingestive behavior (MIB) in the free-living population. Our research has shown that frequency of swallowing may serve as a predictor for detecting food intake, differentiating liquids and solids, and estimating ingested mass. This paper proposes and compares two methods of acoustical swallowing detection from sounds contaminated by motion artifacts, speech, and external noise. Methods based on mel-scale Fourier spectrum, wavelet packets, and support vector machines are studied considering the effects of epoch size, level of decomposition, and lagging on classification accuracy. The methodology was tested on a large dataset (64.5 h with a total of 9966 swallows) collected from 20 human subjects with various degrees of adiposity. Average weighted epoch-recognition accuracy for intravisit individual models was 96.8%, which resulted in 84.7% average weighted accuracy in detection of swallowing events. These results suggest high efficiency of the proposed methodology in separation of swallowing sounds from artifacts that originate from respiration, intrinsic speech, head movements, food ingestion, and ambient noise. The recognition accuracy was not related to body mass index, suggesting that the methodology is suitable for obese individuals.

Automatic Detection of Swallowing Events by Acoustical Means for Applications of Monitoring of Ingestive Behavior

PubMed Central

Sazonov, Edward S.; Makeyev, Oleksandr; Schuckers, Stephanie; Lopez-Meyer, Paulo; Melanson, Edward L.; Neuman, Michael R.

2010-01-01

Our understanding of etiology of obesity and overweight is incomplete due to lack of objective and accurate methods for Monitoring of Ingestive Behavior (MIB) in the free living population. Our research has shown that frequency of swallowing may serve as a predictor for detecting food intake, differentiating liquids and solids, and estimating ingested mass. This paper proposes and compares two methods of acoustical swallowing detection from sounds contaminated by motion artifacts, speech and external noise. Methods based on mel-scale Fourier spectrum, wavelet packets, and support vector machines are studied considering the effects of epoch size, level of decomposition and lagging on classification accuracy. The methodology was tested on a large dataset (64.5 hours with a total of 9,966 swallows) collected from 20 human subjects with various degrees of adiposity. Average weighted epoch recognition accuracy for intra-visit individual models was 96.8% which resulted in 84.7% average weighted accuracy in detection of swallowing events. These results suggest high efficiency of the proposed methodology in separation of swallowing sounds from artifacts that originate from respiration, intrinsic speech, head movements, food ingestion, and ambient noise. The recognition accuracy was not related to body mass index, suggesting that the methodology is suitable for obese individuals. PMID:19789095

Noise Robust Speech Recognition Applied to Voice-Driven Wheelchair

NASA Astrophysics Data System (ADS)

Sasou, Akira; Kojima, Hiroaki

2009-12-01

Conventional voice-driven wheelchairs usually employ headset microphones that are capable of achieving sufficient recognition accuracy, even in the presence of surrounding noise. However, such interfaces require users to wear sensors such as a headset microphone, which can be an impediment, especially for the hand disabled. Conversely, it is also well known that the speech recognition accuracy drastically degrades when the microphone is placed far from the user. In this paper, we develop a noise robust speech recognition system for a voice-driven wheelchair. This system can achieve almost the same recognition accuracy as the headset microphone without wearing sensors. We verified the effectiveness of our system in experiments in different environments, and confirmed that our system can achieve almost the same recognition accuracy as the headset microphone without wearing sensors.

The Effect of Remote Masking on the Reception of Speech by Young School-Age Children.

PubMed

Youngdahl, Carla L; Healy, Eric W; Yoho, Sarah E; Apoux, Frédéric; Holt, Rachael Frush

2018-02-15

Psychoacoustic data indicate that infants and children are less likely than adults to focus on a spectral region containing an anticipated signal and are more susceptible to remote masking of a signal. These detection tasks suggest that infants and children, unlike adults, do not listen selectively. However, less is known about children's ability to listen selectively during speech recognition. Accordingly, the current study examines remote masking during speech recognition in children and adults. Adults and 7- and 5-year-old children performed sentence recognition in the presence of various spectrally remote maskers. Intelligibility was determined for each remote-masker condition, and performance was compared across age groups. It was found that speech recognition for 5-year-olds was reduced in the presence of spectrally remote noise, whereas the maskers had no effect on the 7-year-olds or adults. Maskers of different bandwidth and remoteness had similar effects. In accord with psychoacoustic data, young children do not appear to focus on a spectral region of interest and ignore other regions during speech recognition. This tendency may help account for their typically poorer speech perception in noise. This study also appears to capture an important developmental stage, during which a substantial refinement in spectral listening occurs.

Speech Recognition in Noise by Children with and without Dyslexia: How is it Related to Reading?

PubMed

Nittrouer, Susan; Krieg, Letitia M; Lowenstein, Joanna H

2018-06-01

Developmental dyslexia is commonly viewed as a phonological deficit that makes it difficult to decode written language. But children with dyslexia typically exhibit other problems, as well, including poor speech recognition in noise. The purpose of this study was to examine whether the speech-in-noise problems of children with dyslexia are related to their reading problems, and if so, if a common underlying factor might explain both. The specific hypothesis examined was that a spectral processing disorder results in these children receiving smeared signals, which could explain both the diminished sensitivity to phonological structure - leading to reading problems - and the speech recognition in noise difficulties. The alternative hypothesis tested in this study was that children with dyslexia simply have broadly based language deficits. Ninety-seven children between the ages of 7 years; 10 months and 12 years; 9 months participated: 46 with dyslexia and 51 without dyslexia. Children were tested on two dependent measures: word reading and recognition in noise with two types of sentence materials: as unprocessed (UP) signals, and as spectrally smeared (SM) signals. Data were collected for four predictor variables: phonological awareness, vocabulary, grammatical knowledge, and digit span. Children with dyslexia showed deficits on both dependent and all predictor variables. Their scores for speech recognition in noise were poorer than those of children without dyslexia for both the UP and SM signals, but by equivalent amounts across signal conditions indicating that they were not disproportionately hindered by spectral distortion. Correlation analyses on scores from children with dyslexia showed that reading ability and speech-in-noise recognition were only mildly correlated, and each skill was related to different underlying abilities. No substantial evidence was found to support the suggestion that the reading and speech recognition in noise problems of children with dyslexia arise from a single factor that could be defined as a spectral processing disorder. The reading and speech recognition in noise deficits of these children appeared to be largely independent. Copyright © 2018 Elsevier Ltd. All rights reserved.

Schizophrenia alters intra-network functional connectivity in the caudate for detecting speech under informational speech masking conditions.

PubMed

Zheng, Yingjun; Wu, Chao; Li, Juanhua; Li, Ruikeng; Peng, Hongjun; She, Shenglin; Ning, Yuping; Li, Liang

2018-04-04

Speech recognition under noisy "cocktail-party" environments involves multiple perceptual/cognitive processes, including target detection, selective attention, irrelevant signal inhibition, sensory/working memory, and speech production. Compared to health listeners, people with schizophrenia are more vulnerable to masking stimuli and perform worse in speech recognition under speech-on-speech masking conditions. Although the schizophrenia-related speech-recognition impairment under "cocktail-party" conditions is associated with deficits of various perceptual/cognitive processes, it is crucial to know whether the brain substrates critically underlying speech detection against informational speech masking are impaired in people with schizophrenia. Using functional magnetic resonance imaging (fMRI), this study investigated differences between people with schizophrenia (n = 19, mean age = 33 ± 10 years) and their matched healthy controls (n = 15, mean age = 30 ± 9 years) in intra-network functional connectivity (FC) specifically associated with target-speech detection under speech-on-speech-masking conditions. The target-speech detection performance under the speech-on-speech-masking condition in participants with schizophrenia was significantly worse than that in matched healthy participants (healthy controls). Moreover, in healthy controls, but not participants with schizophrenia, the strength of intra-network FC within the bilateral caudate was positively correlated with the speech-detection performance under the speech-masking conditions. Compared to controls, patients showed altered spatial activity pattern and decreased intra-network FC in the caudate. In people with schizophrenia, the declined speech-detection performance under speech-on-speech masking conditions is associated with reduced intra-caudate functional connectivity, which normally contributes to detecting target speech against speech masking via its functions of suppressing masking-speech signals.

Application of advanced speech technology in manned penetration bombers

NASA Astrophysics Data System (ADS)

North, R.; Lea, W.

1982-03-01

This report documents research on the potential use of speech technology in a manned penetration bomber aircraft (B-52/G and H). The objectives of the project were to analyze the pilot/copilot crewstation tasks over a three-hour-and forty-minute mission and determine the tasks that would benefit the most from conversion to speech recognition/generation, determine the technological feasibility of each of the identified tasks, and prioritize these tasks based on these criteria. Secondary objectives of the program were to enunciate research strategies in the application of speech technologies in airborne environments, and develop guidelines for briefing user commands on the potential of using speech technologies in the cockpit. The results of this study indicated that for the B-52 crewmember, speech recognition would be most beneficial for retrieving chart and procedural data that is contained in the flight manuals. Technological feasibility of these tasks indicated that the checklist and procedural retrieval tasks would be highly feasible for a speech recognition system.

On the Use of Evolutionary Algorithms to Improve the Robustness of Continuous Speech Recognition Systems in Adverse Conditions

NASA Astrophysics Data System (ADS)

Selouani, Sid-Ahmed; O'Shaughnessy, Douglas

2003-12-01

Limiting the decrease in performance due to acoustic environment changes remains a major challenge for continuous speech recognition (CSR) systems. We propose a novel approach which combines the Karhunen-Loève transform (KLT) in the mel-frequency domain with a genetic algorithm (GA) to enhance the data representing corrupted speech. The idea consists of projecting noisy speech parameters onto the space generated by the genetically optimized principal axis issued from the KLT. The enhanced parameters increase the recognition rate for highly interfering noise environments. The proposed hybrid technique, when included in the front-end of an HTK-based CSR system, outperforms that of the conventional recognition process in severe interfering car noise environments for a wide range of signal-to-noise ratios (SNRs) varying from 16 dB to[InlineEquation not available: see fulltext.] dB. We also showed the effectiveness of the KLT-GA method in recognizing speech subject to telephone channel degradations.

How linguistic closure and verbal working memory relate to speech recognition in noise--a review.

PubMed

Besser, Jana; Koelewijn, Thomas; Zekveld, Adriana A; Kramer, Sophia E; Festen, Joost M

2013-06-01

The ability to recognize masked speech, commonly measured with a speech reception threshold (SRT) test, is associated with cognitive processing abilities. Two cognitive factors frequently assessed in speech recognition research are the capacity of working memory (WM), measured by means of a reading span (Rspan) or listening span (Lspan) test, and the ability to read masked text (linguistic closure), measured by the text reception threshold (TRT). The current article provides a review of recent hearing research that examined the relationship of TRT and WM span to SRTs in various maskers. Furthermore, modality differences in WM capacity assessed with the Rspan compared to the Lspan test were examined and related to speech recognition abilities in an experimental study with young adults with normal hearing (NH). Span scores were strongly associated with each other, but were higher in the auditory modality. The results of the reviewed studies suggest that TRT and WM span are related to each other, but differ in their relationships with SRT performance. In NH adults of middle age or older, both TRT and Rspan were associated with SRTs in speech maskers, whereas TRT better predicted speech recognition in fluctuating nonspeech maskers. The associations with SRTs in steady-state noise were inconclusive for both measures. WM span was positively related to benefit from contextual information in speech recognition, but better TRTs related to less interference from unrelated cues. Data for individuals with impaired hearing are limited, but larger WM span seems to give a general advantage in various listening situations.

How Linguistic Closure and Verbal Working Memory Relate to Speech Recognition in Noise—A Review

PubMed Central

Koelewijn, Thomas; Zekveld, Adriana A.; Kramer, Sophia E.; Festen, Joost M.

2013-01-01

The ability to recognize masked speech, commonly measured with a speech reception threshold (SRT) test, is associated with cognitive processing abilities. Two cognitive factors frequently assessed in speech recognition research are the capacity of working memory (WM), measured by means of a reading span (Rspan) or listening span (Lspan) test, and the ability to read masked text (linguistic closure), measured by the text reception threshold (TRT). The current article provides a review of recent hearing research that examined the relationship of TRT and WM span to SRTs in various maskers. Furthermore, modality differences in WM capacity assessed with the Rspan compared to the Lspan test were examined and related to speech recognition abilities in an experimental study with young adults with normal hearing (NH). Span scores were strongly associated with each other, but were higher in the auditory modality. The results of the reviewed studies suggest that TRT and WM span are related to each other, but differ in their relationships with SRT performance. In NH adults of middle age or older, both TRT and Rspan were associated with SRTs in speech maskers, whereas TRT better predicted speech recognition in fluctuating nonspeech maskers. The associations with SRTs in steady-state noise were inconclusive for both measures. WM span was positively related to benefit from contextual information in speech recognition, but better TRTs related to less interference from unrelated cues. Data for individuals with impaired hearing are limited, but larger WM span seems to give a general advantage in various listening situations. PMID:23945955

The Effect of Dynamic Pitch on Speech Recognition in Temporally Modulated Noise

ERIC Educational Resources Information Center

Shen, Jung; Souza, Pamela E.

2017-01-01

Purpose: This study investigated the effect of dynamic pitch in target speech on older and younger listeners' speech recognition in temporally modulated noise. First, we examined whether the benefit from dynamic-pitch cues depends on the temporal modulation of noise. Second, we tested whether older listeners can benefit from dynamic-pitch cues for…

Introduction and Overview of the Vicens-Reddy Speech Recognition System.

ERIC Educational Resources Information Center

Kameny, Iris; Ritea, H.

The Vicens-Reddy System is unique in the sense that it approaches the problem of speech recognition as a whole, rather than treating particular aspects of the problems as in previous attempts. For example, where earlier systems treated only segmentation of speech into phoneme groups, or detected phonemes in a given context, the Vicens-Reddy System…

Accommodation and Compliance Series: Employees with Arthritis

MedlinePlus

... handed keyboard, an articulating keyboard tray, speech recognition software, a trackball, and office equipment for a workstation ... space heater, additional window insulation, and speech recognition software. An insurance clerk with arthritis from systemic lupus ...

[Research on Barrier-free Home Environment System Based on Speech Recognition].

PubMed

Zhu, Husheng; Yu, Hongliu; Shi, Ping; Fang, Youfang; Jian, Zhuo

2015-10-01

The number of people with physical disabilities is increasing year by year, and the trend of population aging is more and more serious. In order to improve the quality of the life, a control system of accessible home environment for the patients with serious disabilities was developed to control the home electrical devices with the voice of the patients. The control system includes a central control platform, a speech recognition module, a terminal operation module, etc. The system combines the speech recognition control technology and wireless information transmission technology with the embedded mobile computing technology, and interconnects the lamp, electronic locks, alarms, TV and other electrical devices in the home environment as a whole system through a wireless network node. The experimental results showed that speech recognition success rate was more than 84% in the home environment.

Speech-recognition interfaces for music information retrieval

NASA Astrophysics Data System (ADS)

Goto, Masataka

2005-09-01

This paper describes two hands-free music information retrieval (MIR) systems that enable a user to retrieve and play back a musical piece by saying its title or the artist's name. Although various interfaces for MIR have been proposed, speech-recognition interfaces suitable for retrieving musical pieces have not been studied. Our MIR-based jukebox systems employ two different speech-recognition interfaces for MIR, speech completion and speech spotter, which exploit intentionally controlled nonverbal speech information in original ways. The first is a music retrieval system with the speech-completion interface that is suitable for music stores and car-driving situations. When a user only remembers part of the name of a musical piece or an artist and utters only a remembered fragment, the system helps the user recall and enter the name by completing the fragment. The second is a background-music playback system with the speech-spotter interface that can enrich human-human conversation. When a user is talking to another person, the system allows the user to enter voice commands for music playback control by spotting a special voice-command utterance in face-to-face or telephone conversations. Experimental results from use of these systems have demonstrated the effectiveness of the speech-completion and speech-spotter interfaces. (Video clips: http://staff.aist.go.jp/m.goto/MIR/speech-if.html)

Syntax-directed content analysis of videotext: application to a map detection recognition system

NASA Astrophysics Data System (ADS)

Aradhye, Hrishikesh; Herson, James A.; Myers, Gregory

2003-01-01

Video is an increasingly important and ever-growing source of information to the intelligence and homeland defense analyst. A capability to automatically identify the contents of video imagery would enable the analyst to index relevant foreign and domestic news videos in a convenient and meaningful way. To this end, the proposed system aims to help determine the geographic focus of a news story directly from video imagery by detecting and geographically localizing political maps from news broadcasts, using the results of videotext recognition in lieu of a computationally expensive, scale-independent shape recognizer. Our novel method for the geographic localization of a map is based on the premise that the relative placement of text superimposed on a map roughly corresponds to the geographic coordinates of the locations the text represents. Our scheme extracts and recognizes videotext, and iteratively identifies the geographic area, while allowing for OCR errors and artistic freedom. The fast and reliable recognition of such maps by our system may provide valuable context and supporting evidence for other sources, such as speech recognition transcripts. The concepts of syntax-directed content analysis of videotext presented here can be extended to other content analysis systems.

Recognition of Speech from the Television with Use of a Wireless Technology Designed for Cochlear Implants.

PubMed

Duke, Mila Morais; Wolfe, Jace; Schafer, Erin

2016-05-01

Cochlear implant (CI) recipients often experience difficulty understanding speech in noise and speech that originates from a distance. Many CI recipients also experience difficulty understanding speech originating from a television. Use of hearing assistance technology (HAT) may improve speech recognition in noise and for signals that originate from more than a few feet from the listener; however, there are no published studies evaluating the potential benefits of a wireless HAT designed to deliver audio signals from a television directly to a CI sound processor. The objective of this study was to compare speech recognition in quiet and in noise of CI recipients with the use of their CI alone and with the use of their CI and a wireless HAT (Cochlear Wireless TV Streamer). A two-way repeated measures design was used to evaluate performance differences obtained in quiet and in competing noise (65 dBA) with the CI sound processor alone and with the sound processor coupled to the Cochlear Wireless TV Streamer. Sixteen users of Cochlear Nucleus 24 Freedom, CI512, and CI422 implants were included in the study. Participants were evaluated in four conditions including use of the sound processor alone and use of the sound processor with the wireless streamer in quiet and in the presence of competing noise at 65 dBA. Speech recognition was evaluated in each condition with two full lists of Computer-Assisted Speech Perception Testing and Training Sentence-Level Test sentences presented from a light-emitting diode television. Speech recognition in noise was significantly better with use of the wireless streamer compared to participants' performance with their CI sound processor alone. There was also a nonsignificant trend toward better performance in quiet with use of the TV Streamer. Performance was significantly poorer when evaluated in noise compared to performance in quiet when the TV Streamer was not used. Use of the Cochlear Wireless TV Streamer designed to stream audio from a television directly to a CI sound processor provides better speech recognition in quiet and in noise when compared to performance obtained with use of the CI sound processor alone. American Academy of Audiology.

Institute for the Study of Human Capabilities Summary Descriptions of Research for the Period September 1988 through June 1989

DTIC Science & Technology

1989-06-01

12 1.7 Application of the Modified Speech Transmission Index to Monaural and Binaural Speech Recognition in Normal and Impaired...describe all of the data from both groups. 1.7 Application of the Modified Speech Transmission Index to Monaural and Binaural Speech Recognition in...were obtained for materials presented to each ear separately (monaurally) and to both ears ( binaurally ). Results from the normal listeners are accurately

Emotion recognition from speech: tools and challenges

NASA Astrophysics Data System (ADS)

Al-Talabani, Abdulbasit; Sellahewa, Harin; Jassim, Sabah A.

2015-05-01

Human emotion recognition from speech is studied frequently for its importance in many applications, e.g. human-computer interaction. There is a wide diversity and non-agreement about the basic emotion or emotion-related states on one hand and about where the emotion related information lies in the speech signal on the other side. These diversities motivate our investigations into extracting Meta-features using the PCA approach, or using a non-adaptive random projection RP, which significantly reduce the large dimensional speech feature vectors that may contain a wide range of emotion related information. Subsets of Meta-features are fused to increase the performance of the recognition model that adopts the score-based LDC classifier. We shall demonstrate that our scheme outperform the state of the art results when tested on non-prompted databases or acted databases (i.e. when subjects act specific emotions while uttering a sentence). However, the huge gap between accuracy rates achieved on the different types of datasets of speech raises questions about the way emotions modulate the speech. In particular we shall argue that emotion recognition from speech should not be dealt with as a classification problem. We shall demonstrate the presence of a spectrum of different emotions in the same speech portion especially in the non-prompted data sets, which tends to be more "natural" than the acted datasets where the subjects attempt to suppress all but one emotion.

Emotion Recognition from Chinese Speech for Smart Affective Services Using a Combination of SVM and DBN

PubMed Central

Zhu, Lianzhang; Chen, Leiming; Zhao, Dehai

2017-01-01

Accurate emotion recognition from speech is important for applications like smart health care, smart entertainment, and other smart services. High accuracy emotion recognition from Chinese speech is challenging due to the complexities of the Chinese language. In this paper, we explore how to improve the accuracy of speech emotion recognition, including speech signal feature extraction and emotion classification methods. Five types of features are extracted from a speech sample: mel frequency cepstrum coefficient (MFCC), pitch, formant, short-term zero-crossing rate and short-term energy. By comparing statistical features with deep features extracted by a Deep Belief Network (DBN), we attempt to find the best features to identify the emotion status for speech. We propose a novel classification method that combines DBN and SVM (support vector machine) instead of using only one of them. In addition, a conjugate gradient method is applied to train DBN in order to speed up the training process. Gender-dependent experiments are conducted using an emotional speech database created by the Chinese Academy of Sciences. The results show that DBN features can reflect emotion status better than artificial features, and our new classification approach achieves an accuracy of 95.8%, which is higher than using either DBN or SVM separately. Results also show that DBN can work very well for small training databases if it is properly designed. PMID:28737705

Towards the identification of Idiopathic Parkinson’s Disease from the speech. New articulatory kinetic biomarkers

PubMed Central

Shattuck-Hufnagel, S.; Choi, J. Y.; Moro-Velázquez, L.; Gómez-García, J. A.

2017-01-01

Although a large amount of acoustic indicators have already been proposed in the literature to evaluate the hypokinetic dysarthria of people with Parkinson’s Disease, the goal of this work is to identify and interpret new reliable and complementary articulatory biomarkers that could be applied to predict/evaluate Parkinson’s Disease from a diadochokinetic test, contributing to the possibility of a further multidimensional analysis of the speech of parkinsonian patients. The new biomarkers proposed are based on the kinetic behaviour of the envelope trace, which is directly linked with the articulatory dysfunctions introduced by the disease since the early stages. The interest of these new articulatory indicators stands on their easiness of identification and interpretation, and their potential to be translated into computer based automatic methods to screen the disease from the speech. Throughout this paper, the accuracy provided by these acoustic kinetic biomarkers is compared with the one obtained with a baseline system based on speaker identification techniques. Results show accuracies around 85% that are in line with those obtained with the complex state of the art speaker recognition techniques, but with an easier physical interpretation, which open the possibility to be transferred to a clinical setting. PMID:29240814

On the context dependency of implicit self-esteem in social anxiety disorder.

PubMed

Hiller, Thomas S; Steffens, Melanie C; Ritter, Viktoria; Stangier, Ulrich

2017-12-01

Cognitive models assume that negative self-evaluations are automatically activated in individuals with Social Anxiety Disorder (SAD) during social situations, increasing their individual level of anxiety. This study examined automatic self-evaluations (i.e., implicit self-esteem) and state anxiety in a group of individuals with SAD (n = 45) and a non-clinical comparison group (NC; n = 46). Participants were randomly assigned to either a speech condition with social threat induction (giving an impromptu speech) or to a no-speech condition without social threat induction. We measured implicit self-esteem with an Implicit Association Test (IAT). Implicit self-esteem differed significantly between SAD and NC groups under the speech condition but not under the no-speech condition. The SAD group showed lower implicit self-esteem than the NC group under the speech-condition. State anxiety was significantly higher under the speech condition than under the no-speech condition in the SAD group but not in the NC group. Mediation analyses supported the idea that for the SAD group, the effect of experimental condition on state anxiety was mediated by implicit self-esteem. The causal relation between implicit self-esteem and state anxiety could not be determined. The findings corroborate hypotheses derived from cognitive models of SAD: Automatic self-evaluations were negatively biased in individuals with SAD facing social threat and showed an inverse relationship to levels of state anxiety. However, automatic self-evaluations in individuals with SAD can be unbiased (similar to NC) in situations without social threat. Copyright © 2017 Elsevier Ltd. All rights reserved.

Automatic Title Generation for Spoken Broadcast News

DTIC Science & Technology

2001-01-01

degrades much less with speech -recognized transcripts. Meanwhile, even though KNN performance not as well as TF.IDF and NBL in terms of F1 metric, it...test corpus of 1006 broadcast news documents, comparing the results over manual transcription to the results over automatically recognized speech . We...use both F1 and the average number of correct title words in the correct order as metric. Overall, the results show that title generation for speech

Hearing Handicap and Speech Recognition Correlate With Self-Reported Listening Effort and Fatigue.

PubMed

Alhanbali, Sara; Dawes, Piers; Lloyd, Simon; Munro, Kevin J

To investigate the correlations between hearing handicap, speech recognition, listening effort, and fatigue. Eighty-four adults with hearing loss (65 to 85 years) completed three self-report questionnaires: the Fatigue Assessment Scale, the Effort Assessment Scale, and the Hearing Handicap Inventory for Elderly. Audiometric assessment included pure-tone audiometry and speech recognition in noise. There was a significant positive correlation between handicap and fatigue (r = 0.39, p < 0.05) and handicap and effort (r = 0.73, p < 0.05). There were significant (but lower) correlations between speech recognition and fatigue (r = 0.22, p < 0.05) or effort (r = 0.32, p< 0.05). There was no significant correlation between hearing level and fatigue or effort. Hearing handicap and speech recognition both correlate with self-reported listening effort and fatigue, which is consistent with a model of listening effort and fatigue where perceived difficulty is related to sustained effort and fatigue for unrewarding tasks over which the listener has low control. A clinical implication is that encouraging clients to recognize and focus on the pleasure and positive experiences of listening may result in greater satisfaction and benefit from hearing aid use.

Financial and workflow analysis of radiology reporting processes in the planning phase of implementation of a speech recognition system

NASA Astrophysics Data System (ADS)

Whang, Tom; Ratib, Osman M.; Umamoto, Kathleen; Grant, Edward G.; McCoy, Michael J.

2002-05-01

The goal of this study is to determine the financial value and workflow improvements achievable by replacing traditional transcription services with a speech recognition system in a large, university hospital setting. Workflow metrics were measured at two hospitals, one of which exclusively uses a transcription service (UCLA Medical Center), and the other which exclusively uses speech recognition (West Los Angeles VA Hospital). Workflow metrics include time spent per report (the sum of time spent interpreting, dictating, reviewing, and editing), transcription turnaround, and total report turnaround. Compared to traditional transcription, speech recognition resulted in radiologists spending 13-32% more time per report, but it also resulted in reduction of report turnaround time by 22-62% and reduction of marginal cost per report by 94%. The model developed here helps justify the introduction of a speech recognition system by showing that the benefits of reduced operating costs and decreased turnaround time outweigh the cost of increased time spent per report. Whether the ultimate goal is to achieve a financial objective or to improve operational efficiency, it is important to conduct a thorough analysis of workflow before implementation.

Effects of cooperating and conflicting cues on speech intonation recognition by cochlear implant users and normal hearing listeners.

PubMed

Peng, Shu-Chen; Lu, Nelson; Chatterjee, Monita

2009-01-01

Cochlear implant (CI) recipients have only limited access to fundamental frequency (F0) information, and thus exhibit deficits in speech intonation recognition. For speech intonation, F0 serves as the primary cue, and other potential acoustic cues (e.g. intensity properties) may also contribute. This study examined the effects of cooperating or conflicting acoustic cues on speech intonation recognition by adult CI and normal hearing (NH) listeners with full-spectrum and spectrally degraded speech stimuli. Identification of speech intonation that signifies question and statement contrasts was measured in 13 CI recipients and 4 NH listeners, using resynthesized bi-syllabic words, where F0 and intensity properties were systematically manipulated. The stimulus set was comprised of tokens whose acoustic cues (i.e. F0 contour and intensity patterns) were either cooperating or conflicting. Subjects identified if each stimulus is a 'statement' or a 'question' in a single-interval, 2-alternative forced-choice (2AFC) paradigm. Logistic models were fitted to the data, and estimated coefficients were compared under cooperating and conflicting conditions, between the subject groups (CI vs. NH), and under full-spectrum and spectrally degraded conditions for NH listeners. The results indicated that CI listeners' intonation recognition was enhanced by cooperating F0 contour and intensity cues, but was adversely affected by these cues being conflicting. On the other hand, with full-spectrum stimuli, NH listeners' intonation recognition was not affected by cues being cooperating or conflicting. The effects of cues being cooperating or conflicting were comparable between the CI group and NH listeners with spectrally degraded stimuli. These findings suggest the importance of taking multiple acoustic sources for speech recognition into consideration in aural rehabilitation for CI recipients. Copyright (C) 2009 S. Karger AG, Basel.

Effects of cooperating and conflicting cues on speech intonation recognition by cochlear implant users and normal hearing listeners

PubMed Central

Peng, Shu-Chen; Lu, Nelson; Chatterjee, Monita

2009-01-01

Cochlear implant (CI) recipients have only limited access to fundamental frequency (F0) information, and thus exhibit deficits in speech intonation recognition. For speech intonation, F0 serves as the primary cue, and other potential acoustic cues (e.g., intensity properties) may also contribute. This study examined the effects of acoustic cues being cooperating or conflicting on speech intonation recognition by adult cochlear implant (CI), and normal-hearing (NH) listeners with full-spectrum and spectrally degraded speech stimuli. Identification of speech intonation that signifies question and statement contrasts was measured in 13 CI recipients and 4 NH listeners, using resynthesized bi-syllabic words, where F0 and intensity properties were systematically manipulated. The stimulus set was comprised of tokens whose acoustic cues, i.e., F0 contour and intensity patterns, were either cooperating or conflicting. Subjects identified if each stimulus is a “statement” or a “question” in a single-interval, two-alternative forced-choice (2AFC) paradigm. Logistic models were fitted to the data, and estimated coefficients were compared under cooperating and conflicting conditions, between the subject groups (CI vs. NH), and under full-spectrum and spectrally degraded conditions for NH listeners. The results indicated that CI listeners’ intonation recognition was enhanced by F0 contour and intensity cues being cooperating, but was adversely affected by these cues being conflicting. On the other hand, with full-spectrum stimuli, NH listeners’ intonation recognition was not affected by cues being cooperating or conflicting. The effects of cues being cooperating or conflicting were comparable between the CI group and NH listeners with spectrally-degraded stimuli. These findings suggest the importance of taking multiple acoustic sources for speech recognition into consideration in aural rehabilitation for CI recipients. PMID:19372651

Improving Mobile Phone Speech Recognition by Personalized Amplification: Application in People with Normal Hearing and Mild-to-Moderate Hearing Loss.

PubMed

Kam, Anna Chi Shan; Sung, John Ka Keung; Lee, Tan; Wong, Terence Ka Cheong; van Hasselt, Andrew

In this study, the authors evaluated the effect of personalized amplification on mobile phone speech recognition in people with and without hearing loss. This prospective study used double-blind, within-subjects, repeated measures, controlled trials to evaluate the effectiveness of applying personalized amplification based on the hearing level captured on the mobile device. The personalized amplification settings were created using modified one-third gain targets. The participants in this study included 100 adults of age between 20 and 78 years (60 with age-adjusted normal hearing and 40 with hearing loss). The performance of the participants with personalized amplification and standard settings was compared using both subjective and speech-perception measures. Speech recognition was measured in quiet and in noise using Cantonese disyllabic words. Subjective ratings on the quality, clarity, and comfortableness of the mobile signals were measured with an 11-point visual analog scale. Subjective preferences of the settings were also obtained by a paired-comparison procedure. The personalized amplification application provided better speech recognition via the mobile phone both in quiet and in noise for people with hearing impairment (improved 8 to 10%) and people with normal hearing (improved 1 to 4%). The improvement in speech recognition was significantly better for people with hearing impairment. When the average device output level was matched, more participants preferred to have the individualized gain than not to have it. The personalized amplification application has the potential to improve speech recognition for people with mild-to-moderate hearing loss, as well as people with normal hearing, in particular when listening in noisy environments.

Study of environmental sound source identification based on hidden Markov model for robust speech recognition

NASA Astrophysics Data System (ADS)

Nishiura, Takanobu; Nakamura, Satoshi

2003-10-01

Humans communicate with each other through speech by focusing on the target speech among environmental sounds in real acoustic environments. We can easily identify the target sound from other environmental sounds. For hands-free speech recognition, the identification of the target speech from environmental sounds is imperative. This mechanism may also be important for a self-moving robot to sense the acoustic environments and communicate with humans. Therefore, this paper first proposes hidden Markov model (HMM)-based environmental sound source identification. Environmental sounds are modeled by three states of HMMs and evaluated using 92 kinds of environmental sounds. The identification accuracy was 95.4%. This paper also proposes a new HMM composition method that composes speech HMMs and an HMM of categorized environmental sounds for robust environmental sound-added speech recognition. As a result of the evaluation experiments, we confirmed that the proposed HMM composition outperforms the conventional HMM composition with speech HMMs and a noise (environmental sound) HMM trained using noise periods prior to the target speech in a captured signal. [Work supported by Ministry of Public Management, Home Affairs, Posts and Telecommunications of Japan.

Neural network-based recognition of whistlers on spectrograms detected by satellite

NASA Astrophysics Data System (ADS)

Conti, Livio

2016-04-01

We present a system to automatically recognize and classify the occurrence of whistler waves on spectrograms of electric field measurements performed by satellite. Whistlers - VLF waves generated by lightning, with a specific spectral dispersion relation - can induce precipitation of trapped Van Allen particles and have a role in the chemistry of some atmospheric components (mainly NOx). Moreover, it has also been suggested that the increase of the number of anomalous whistlers (i.e. whistlers with high value of dispersion constant) could be induced by disturbances in the Earth-ionosphere wave-guide, generated by seismo-electromagnetic emissions. On satellite, the recognition of whistlers asks for analyzing high-resolution spectrograms that cannot be downloaded to Earth, due to the limits of data transmission. For this reason, a real time identification and classification must be performed on satellite, by avoiding downloading all the unprocessed data. The procedure that we have developed is based on a Time Delay Neural Network (TDNN). The TDNN, proposed some years ago for speech recognition, can be fruitfully also applied in real-time analysis of electromagnetic spectrograms in order to detect phenomena characterized by a specific shape/signature such as those of the whistler waves. Some studies have been performed by the RNF experiment on board of the DEMETER satellite and our algorithm could be adopted on board of the satellite CSES (China Seismo-Electromagnetic Satellite), launch scheduled by the end of 2016. Moreover, the procedure can be also adopted to automatic analysis of whistlers detected on ground.

Detecting buried explosive hazards with handheld GPR and deep learning

NASA Astrophysics Data System (ADS)

Besaw, Lance E.

2016-05-01

Buried explosive hazards (BEHs), including traditional landmines and homemade improvised explosives, have proven difficult to detect and defeat during and after conflicts around the world. Despite their various sizes, shapes and construction material, ground penetrating radar (GPR) is an excellent phenomenology for detecting BEHs due to its ability to sense localized differences in electromagnetic properties. Handheld GPR detectors are common equipment for detecting BEHs because of their flexibility (in part due to the human operator) and effectiveness in cluttered environments. With modern digital electronics and positioning systems, handheld GPR sensors can sense and map variation in electromagnetic properties while searching for BEHs. Additionally, large-scale computers have demonstrated an insatiable appetite for ingesting massive datasets and extracting meaningful relationships. This is no more evident than the maturation of deep learning artificial neural networks (ANNs) for image and speech recognition now commonplace in industry and academia. This confluence of sensing, computing and pattern recognition technologies offers great potential to develop automatic target recognition techniques to assist GPR operators searching for BEHs. In this work deep learning ANNs are used to detect BEHs and discriminate them from harmless clutter. We apply these techniques to a multi-antennae, handheld GPR with centimeter-accurate positioning system that was used to collect data over prepared lanes containing a wide range of BEHs. This work demonstrates that deep learning ANNs can automatically extract meaningful information from complex GPR signatures, complementing existing GPR anomaly detection and classification techniques.

Speech therapy and voice recognition instrument

NASA Technical Reports Server (NTRS)

Cohen, J.; Babcock, M. L.

1972-01-01

Characteristics of electronic circuit for examining variations in vocal excitation for diagnostic purposes and in speech recognition for determiniog voice patterns and pitch changes are described. Operation of the circuit is discussed and circuit diagram is provided.

An investigation of articulatory setting using real-time magnetic resonance imaging

PubMed Central

Ramanarayanan, Vikram; Goldstein, Louis; Byrd, Dani; Narayanan, Shrikanth S.

2013-01-01

This paper presents an automatic procedure to analyze articulatory setting in speech production using real-time magnetic resonance imaging of the moving human vocal tract. The procedure extracts frames corresponding to inter-speech pauses, speech-ready intervals and absolute rest intervals from magnetic resonance imaging sequences of read and spontaneous speech elicited from five healthy speakers of American English and uses automatically extracted image features to quantify vocal tract posture during these intervals. Statistical analyses show significant differences between vocal tract postures adopted during inter-speech pauses and those at absolute rest before speech; the latter also exhibits a greater variability in the adopted postures. In addition, the articulatory settings adopted during inter-speech pauses in read and spontaneous speech are distinct. The results suggest that adopted vocal tract postures differ on average during rest positions, ready positions and inter-speech pauses, and might, in that order, involve an increasing degree of active control by the cognitive speech planning mechanism. PMID:23862826

Temporal processing of speech in a time-feature space

NASA Astrophysics Data System (ADS)

Avendano, Carlos

1997-09-01

The performance of speech communication systems often degrades under realistic environmental conditions. Adverse environmental factors include additive noise sources, room reverberation, and transmission channel distortions. This work studies the processing of speech in the temporal-feature or modulation spectrum domain, aiming for alleviation of the effects of such disturbances. Speech reflects the geometry of the vocal organs, and the linguistically dominant component is in the shape of the vocal tract. At any given point in time, the shape of the vocal tract is reflected in the short-time spectral envelope of the speech signal. The rate of change of the vocal tract shape appears to be important for the identification of linguistic components. This rate of change, or the rate of change of the short-time spectral envelope can be described by the modulation spectrum, i.e. the spectrum of the time trajectories described by the short-time spectral envelope. For a wide range of frequency bands, the modulation spectrum of speech exhibits a maximum at about 4 Hz, the average syllabic rate. Disturbances often have modulation frequency components outside the speech range, and could in principle be attenuated without significantly affecting the range with relevant linguistic information. Early efforts for exploiting the modulation spectrum domain (temporal processing), such as the dynamic cepstrum or the RASTA processing, used ad hoc designed processing and appear to be suboptimal. As a major contribution, in this dissertation we aim for a systematic data-driven design of temporal processing. First we analytically derive and discuss some properties and merits of temporal processing for speech signals. We attempt to formalize the concept and provide a theoretical background which has been lacking in the field. In the experimental part we apply temporal processing to a number of problems including adaptive noise reduction in cellular telephone environments, reduction of reverberation for speech enhancement, and improvements on automatic recognition of speech degraded by linear distortions and reverberation.

A Development of a System Enables Character Input and PC Operation via Voice for a Physically Disabled Person with a Speech Impediment

NASA Astrophysics Data System (ADS)

Tanioka, Toshimasa; Egashira, Hiroyuki; Takata, Mayumi; Okazaki, Yasuhisa; Watanabe, Kenzi; Kondo, Hiroki

We have designed and implemented a PC operation support system for a physically disabled person with a speech impediment via voice. Voice operation is an effective method for a physically disabled person with involuntary movement of the limbs and the head. We have applied a commercial speech recognition engine to develop our system for practical purposes. Adoption of a commercial engine reduces development cost and will contribute to make our system useful to another speech impediment people. We have customized commercial speech recognition engine so that it can recognize the utterance of a person with a speech impediment. We have restricted the words that the recognition engine recognizes and separated a target words from similar words in pronunciation to avoid misrecognition. Huge number of words registered in commercial speech recognition engines cause frequent misrecognition for speech impediments' utterance, because their utterance is not clear and unstable. We have solved this problem by narrowing the choice of input down in a small number and also by registering their ambiguous pronunciations in addition to the original ones. To realize all character inputs and all PC operation with a small number of words, we have designed multiple input modes with categorized dictionaries and have introduced two-step input in each mode except numeral input to enable correct operation with small number of words. The system we have developed is in practical level. The first author of this paper is physically disabled with a speech impediment. He has been able not only character input into PC but also to operate Windows system smoothly by using this system. He uses this system in his daily life. This paper is written by him with this system. At present, the speech recognition is customized to him. It is, however, possible to customize for other users by changing words and registering new pronunciation according to each user's utterance.

Use of Adaptive Digital Signal Processing to Improve Speech Communication for Normally Hearing aand Hearing-Impaired Subjects.

ERIC Educational Resources Information Center

Harris, Richard W.; And Others

1988-01-01

A two-microphone adaptive digital noise cancellation technique improved word-recognition ability for 20 normal and 12 hearing-impaired adults by reducing multitalker speech babble and speech spectrum noise 18-22 dB. Word recognition improvements averaged 37-50 percent for normal and 27-40 percent for hearing-impaired subjects. Improvement was best…

Multilingual Phoneme Models for Rapid Speech Processing System Development

DTIC Science & Technology

2006-09-01

processes are used to develop an Arabic speech recognition system starting from monolingual English models, In- ternational Phonetic Association (IPA...clusters. It was found that multilingual bootstrapping methods out- perform monolingual English bootstrapping methods on the Arabic evaluation data initially...International Phonetic Alphabet . . . . . . . . . 7 2.3.2 Multilingual vs. Monolingual Speech Recognition 7 2.3.3 Data-Driven Approaches

Effect of a Bluetooth-implemented hearing aid on speech recognition performance: subjective and objective measurement.

PubMed

Kim, Min-Beom; Chung, Won-Ho; Choi, Jeesun; Hong, Sung Hwa; Cho, Yang-Sun; Park, Gyuseok; Lee, Sangmin

2014-06-01

The object was to evaluate speech perception improvement through Bluetooth-implemented hearing aids in hearing-impaired adults. Thirty subjects with bilateral symmetric moderate sensorineural hearing loss participated in this study. A Bluetooth-implemented hearing aid was fitted unilaterally in all study subjects. Objective speech recognition score and subjective satisfaction were measured with a Bluetooth-implemented hearing aid to replace the acoustic connection from either a cellular phone or a loudspeaker system. In each system, participants were assigned to 4 conditions: wireless speech signal transmission into hearing aid (wireless mode) in quiet or noisy environment and conventional speech signal transmission using external microphone of hearing aid (conventional mode) in quiet or noisy environment. Also, participants completed questionnaires to investigate subjective satisfaction. Both cellular phone and loudspeaker system situation, participants showed improvements in sentence and word recognition scores with wireless mode compared to conventional mode in both quiet and noise conditions (P < .001). Participants also reported subjective improvements, including better sound quality, less noise interference, and better accuracy naturalness, when using the wireless mode (P < .001). Bluetooth-implemented hearing aids helped to improve subjective and objective speech recognition performances in quiet and noisy environments during the use of electronic audio devices.

Speech recognition in individuals with sensorineural hearing loss.

PubMed

de Andrade, Adriana Neves; Iorio, Maria Cecilia Martinelli; Gil, Daniela

2016-01-01

Hearing loss can negatively influence the communication performance of individuals, who should be evaluated with suitable material and in situations of listening close to those found in everyday life. To analyze and compare the performance of patients with mild-to-moderate sensorineural hearing loss in speech recognition tests carried out in silence and with noise, according to the variables ear (right and left) and type of stimulus presentation. The study included 19 right-handed individuals with mild-to-moderate symmetrical bilateral sensorineural hearing loss, submitted to the speech recognition test with words in different modalities and speech test with white noise and pictures. There was no significant difference between right and left ears in any of the tests. The mean number of correct responses in the speech recognition test with pictures, live voice, and recorded monosyllables was 97.1%, 85.9%, and 76.1%, respectively, whereas after the introduction of noise, the performance decreased to 72.6% accuracy. The best performances in the Speech Recognition Percentage Index were obtained using monosyllabic stimuli, represented by pictures presented in silence, with no significant differences between the right and left ears. After the introduction of competitive noise, there was a decrease in individuals' performance. Copyright © 2015 Associação Brasileira de Otorrinolaringologia e Cirurgia Cérvico-Facial. Published by Elsevier Editora Ltda. All rights reserved.

Relationships between Structural and Acoustic Properties of Maternal Talk and Children's Early Word Recognition

ERIC Educational Resources Information Center

Suttora, Chiara; Salerni, Nicoletta; Zanchi, Paola; Zampini, Laura; Spinelli, Maria; Fasolo, Mirco

2017-01-01

This study aimed to investigate specific associations between structural and acoustic characteristics of infant-directed (ID) speech and word recognition. Thirty Italian-acquiring children and their mothers were tested when the children were 1;3. Children's word recognition was measured with the looking-while-listening task. Maternal ID speech was…

Speech Recognition in Adults with Cochlear Implants: The Effects of Working Memory, Phonological Sensitivity, and Aging

ERIC Educational Resources Information Center

Moberly, Aaron C.; Harris, Michael S.; Boyce, Lauren; Nittrouer, Susan

2017-01-01

Purpose: Models of speech recognition suggest that "top-down" linguistic and cognitive functions, such as use of phonotactic constraints and working memory, facilitate recognition under conditions of degradation, such as in noise. The question addressed in this study was what happens to these functions when a listener who has experienced…

The Effect of Asymmetrical Signal Degradation on Binaural Speech Recognition in Children and Adults.

ERIC Educational Resources Information Center

Rothpletz, Ann M.; Tharpe, Anne Marie; Grantham, D. Wesley

2004-01-01

To determine the effect of asymmetrical signal degradation on binaural speech recognition, 28 children and 14 adults were administered a sentence recognition task amidst multitalker babble. There were 3 listening conditions: (a) monaural, with mild degradation in 1 ear; (b) binaural, with mild degradation in both ears (symmetric degradation); and…

Learning Models and Real-Time Speech Recognition.

ERIC Educational Resources Information Center

Danforth, Douglas G.; And Others

This report describes the construction and testing of two "psychological" learning models for the purpose of computer recognition of human speech over the telephone. One of the two models was found to be superior in all tests. A regression analysis yielded a 92.3% recognition rate for 14 subjects ranging in age from 6 to 13 years. Tests…

Use of Authentic-Speech Technique for Teaching Sound Recognition to EFL Students

ERIC Educational Resources Information Center

Sersen, William J.

2011-01-01

The main objective of this research was to test an authentic-speech technique for improving the sound-recognition skills of EFL (English as a foreign language) students at Roi-Et Rajabhat University. The secondary objective was to determine the correlation, if any, between students' self-evaluation of sound-recognition progress and the actual…

What happens to the motor theory of perception when the motor system is damaged?

PubMed

Stasenko, Alena; Garcea, Frank E; Mahon, Bradford Z

2013-09-01

Motor theories of perception posit that motor information is necessary for successful recognition of actions. Perhaps the most well known of this class of proposals is the motor theory of speech perception, which argues that speech recognition is fundamentally a process of identifying the articulatory gestures (i.e. motor representations) that were used to produce the speech signal. Here we review neuropsychological evidence from patients with damage to the motor system, in the context of motor theories of perception applied to both manual actions and speech. Motor theories of perception predict that patients with motor impairments will have impairments for action recognition. Contrary to that prediction, the available neuropsychological evidence indicates that recognition can be spared despite profound impairments to production. These data falsify strong forms of the motor theory of perception, and frame new questions about the dynamical interactions that govern how information is exchanged between input and output systems.

What happens to the motor theory of perception when the motor system is damaged?

PubMed Central

Stasenko, Alena; Garcea, Frank E.; Mahon, Bradford Z.

2016-01-01

Motor theories of perception posit that motor information is necessary for successful recognition of actions. Perhaps the most well known of this class of proposals is the motor theory of speech perception, which argues that speech recognition is fundamentally a process of identifying the articulatory gestures (i.e. motor representations) that were used to produce the speech signal. Here we review neuropsychological evidence from patients with damage to the motor system, in the context of motor theories of perception applied to both manual actions and speech. Motor theories of perception predict that patients with motor impairments will have impairments for action recognition. Contrary to that prediction, the available neuropsychological evidence indicates that recognition can be spared despite profound impairments to production. These data falsify strong forms of the motor theory of perception, and frame new questions about the dynamical interactions that govern how information is exchanged between input and output systems. PMID:26823687

Multimodal fusion of polynomial classifiers for automatic person recgonition

NASA Astrophysics Data System (ADS)

Broun, Charles C.; Zhang, Xiaozheng

2001-03-01

With the prevalence of the information age, privacy and personalization are forefront in today's society. As such, biometrics are viewed as essential components of current evolving technological systems. Consumers demand unobtrusive and non-invasive approaches. In our previous work, we have demonstrated a speaker verification system that meets these criteria. However, there are additional constraints for fielded systems. The required recognition transactions are often performed in adverse environments and across diverse populations, necessitating robust solutions. There are two significant problem areas in current generation speaker verification systems. The first is the difficulty in acquiring clean audio signals in all environments without encumbering the user with a head- mounted close-talking microphone. Second, unimodal biometric systems do not work with a significant percentage of the population. To combat these issues, multimodal techniques are being investigated to improve system robustness to environmental conditions, as well as improve overall accuracy across the population. We propose a multi modal approach that builds on our current state-of-the-art speaker verification technology. In order to maintain the transparent nature of the speech interface, we focus on optical sensing technology to provide the additional modality-giving us an audio-visual person recognition system. For the audio domain, we use our existing speaker verification system. For the visual domain, we focus on lip motion. This is chosen, rather than static face or iris recognition, because it provides dynamic information about the individual. In addition, the lip dynamics can aid speech recognition to provide liveness testing. The visual processing method makes use of both color and edge information, combined within Markov random field MRF framework, to localize the lips. Geometric features are extracted and input to a polynomial classifier for the person recognition process. A late integration approach, based on a probabilistic model, is employed to combine the two modalities. The system is tested on the XM2VTS database combined with AWGN in the audio domain over a range of signal-to-noise ratios.

Assessment of Spectral and Temporal Resolution in Cochlear Implant Users Using Psychoacoustic Discrimination and Speech Cue Categorization.

PubMed

Winn, Matthew B; Won, Jong Ho; Moon, Il Joon

This study was conducted to measure auditory perception by cochlear implant users in the spectral and temporal domains, using tests of either categorization (using speech-based cues) or discrimination (using conventional psychoacoustic tests). The authors hypothesized that traditional nonlinguistic tests assessing spectral and temporal auditory resolution would correspond to speech-based measures assessing specific aspects of phonetic categorization assumed to depend on spectral and temporal auditory resolution. The authors further hypothesized that speech-based categorization performance would ultimately be a superior predictor of speech recognition performance, because of the fundamental nature of speech recognition as categorization. Nineteen cochlear implant listeners and 10 listeners with normal hearing participated in a suite of tasks that included spectral ripple discrimination, temporal modulation detection, and syllable categorization, which was split into a spectral cue-based task (targeting the /ba/-/da/ contrast) and a timing cue-based task (targeting the /b/-/p/ and /d/-/t/ contrasts). Speech sounds were manipulated to contain specific spectral or temporal modulations (formant transitions or voice onset time, respectively) that could be categorized. Categorization responses were quantified using logistic regression to assess perceptual sensitivity to acoustic phonetic cues. Word recognition testing was also conducted for cochlear implant listeners. Cochlear implant users were generally less successful at utilizing both spectral and temporal cues for categorization compared with listeners with normal hearing. For the cochlear implant listener group, spectral ripple discrimination was significantly correlated with the categorization of formant transitions; both were correlated with better word recognition. Temporal modulation detection using 100- and 10-Hz-modulated noise was not correlated either with the cochlear implant subjects' categorization of voice onset time or with word recognition. Word recognition was correlated more closely with categorization of the controlled speech cues than with performance on the psychophysical discrimination tasks. When evaluating people with cochlear implants, controlled speech-based stimuli are feasible to use in tests of auditory cue categorization, to complement traditional measures of auditory discrimination. Stimuli based on specific speech cues correspond to counterpart nonlinguistic measures of discrimination, but potentially show better correspondence with speech perception more generally. The ubiquity of the spectral (formant transition) and temporal (voice onset time) stimulus dimensions across languages highlights the potential to use this testing approach even in cases where English is not the native language.

Assessment of spectral and temporal resolution in cochlear implant users using psychoacoustic discrimination and speech cue categorization

PubMed Central

Winn, Matthew B.; Won, Jong Ho; Moon, Il Joon

2016-01-01

Objectives This study was conducted to measure auditory perception by cochlear implant users in the spectral and temporal domains, using tests of either categorization (using speech-based cues) or discrimination (using conventional psychoacoustic tests). We hypothesized that traditional nonlinguistic tests assessing spectral and temporal auditory resolution would correspond to speech-based measures assessing specific aspects of phonetic categorization assumed to depend on spectral and temporal auditory resolution. We further hypothesized that speech-based categorization performance would ultimately be a superior predictor of speech recognition performance, because of the fundamental nature of speech recognition as categorization. Design Nineteen CI listeners and 10 listeners with normal hearing (NH) participated in a suite of tasks that included spectral ripple discrimination (SRD), temporal modulation detection (TMD), and syllable categorization, which was split into a spectral-cue-based task (targeting the /ba/-/da/ contrast) and a timing-cue-based task (targeting the /b/-/p/ and /d/-/t/ contrasts). Speech sounds were manipulated in order to contain specific spectral or temporal modulations (formant transitions or voice onset time, respectively) that could be categorized. Categorization responses were quantified using logistic regression in order to assess perceptual sensitivity to acoustic phonetic cues. Word recognition testing was also conducted for CI listeners. Results CI users were generally less successful at utilizing both spectral and temporal cues for categorization compared to listeners with normal hearing. For the CI listener group, SRD was significantly correlated with the categorization of formant transitions; both were correlated with better word recognition. TMD using 100 Hz and 10 Hz modulated noise was not correlated with the CI subjects’ categorization of VOT, nor with word recognition. Word recognition was correlated more closely with categorization of the controlled speech cues than with performance on the psychophysical discrimination tasks. Conclusions When evaluating people with cochlear implants, controlled speech-based stimuli are feasible to use in tests of auditory cue categorization, to complement traditional measures of auditory discrimination. Stimuli based on specific speech cues correspond to counterpart non-linguistic measures of discrimination, but potentially show better correspondence with speech perception more generally. The ubiquity of the spectral (formant transition) and temporal (VOT) stimulus dimensions across languages highlights the potential to use this testing approach even in cases where English is not the native language. PMID:27438871

Speech variability effects on recognition accuracy associated with concurrent task performance by pilots

NASA Technical Reports Server (NTRS)

Simpson, C. A.

1985-01-01

In the present study of the responses of pairs of pilots to aircraft warning classification tasks using an isolated word, speaker-dependent speech recognition system, the induced stress was manipulated by means of different scoring procedures for the classification task and by the inclusion of a competitive manual control task. Both speech patterns and recognition accuracy were analyzed, and recognition errors were recorded by type for an isolated word speaker-dependent system and by an offline technique for a connected word speaker-dependent system. While errors increased with task loading for the isolated word system, there was no such effect for task loading in the case of the connected word system.

Speech recognition in advanced rotorcraft - Using speech controls to reduce manual control overload

NASA Technical Reports Server (NTRS)

Vidulich, Michael A.; Bortolussi, Michael R.

1988-01-01

An experiment has been conducted to ascertain the usefulness of helicopter pilot speech controls and their effect on time-sharing performance, under the impetus of multiple-resource theories of attention which predict that time-sharing should be more efficient with mixed manual and speech controls than with all-manual ones. The test simulation involved an advanced, single-pilot scout/attack helicopter. Performance and subjective workload levels obtained supported the claimed utility of speech recognition-based controls; specifically, time-sharing performance was improved while preparing a data-burst transmission of information during helicopter hover.

Incorporating Speech Recognition into a Natural User Interface

NASA Technical Reports Server (NTRS)

Chapa, Nicholas

2017-01-01

The Augmented/ Virtual Reality (AVR) Lab has been working to study the applicability of recent virtual and augmented reality hardware and software to KSC operations. This includes the Oculus Rift, HTC Vive, Microsoft HoloLens, and Unity game engine. My project in this lab is to integrate voice recognition and voice commands into an easy to modify system that can be added to an existing portion of a Natural User Interface (NUI). A NUI is an intuitive and simple to use interface incorporating visual, touch, and speech recognition. The inclusion of speech recognition capability will allow users to perform actions or make inquiries using only their voice. The simplicity of needing only to speak to control an on-screen object or enact some digital action means that any user can quickly become accustomed to using this system. Multiple programs were tested for use in a speech command and recognition system. Sphinx4 translates speech to text using a Hidden Markov Model (HMM) based Language Model, an Acoustic Model, and a word Dictionary running on Java. PocketSphinx had similar functionality to Sphinx4 but instead ran on C. However, neither of these programs were ideal as building a Java or C wrapper slowed performance. The most ideal speech recognition system tested was the Unity Engine Grammar Recognizer. A Context Free Grammar (CFG) structure is written in an XML file to specify the structure of phrases and words that will be recognized by Unity Grammar Recognizer. Using Speech Recognition Grammar Specification (SRGS) 1.0 makes modifying the recognized combinations of words and phrases very simple and quick to do. With SRGS 1.0, semantic information can also be added to the XML file, which allows for even more control over how spoken words and phrases are interpreted by Unity. Additionally, using a CFG with SRGS 1.0 produces a Finite State Machine (FSM) functionality limiting the potential for incorrectly heard words or phrases. The purpose of my project was to investigate options for a Speech Recognition System. To that end I attempted to integrate Sphinx4 into a user interface. Sphinx4 had great accuracy and is the only free program able to perform offline speech dictation. However it had a limited dictionary of words that could be recognized, single syllable words were almost impossible for it to hear, and since it ran on Java it could not be integrated into the Unity based NUI. PocketSphinx ran much faster than Sphinx4 which would've made it ideal as a plugin to the Unity NUI, unfortunately creating a C# wrapper for the C code made the program unusable with Unity due to the wrapper slowing code execution and class files becoming unreachable. Unity Grammar Recognizer is the ideal speech recognition interface, it is flexible in recognizing multiple variations of the same command. It is also the most accurate program in recognizing speech due to using an XML grammar to specify speech structure instead of relying solely on a Dictionary and Language model. The Unity Grammar Recognizer will be used with the NUI for these reasons as well as being written in C# which further simplifies the incorporation.

A novel speech processing algorithm based on harmonicity cues in cochlear implant

NASA Astrophysics Data System (ADS)

Wang, Jian; Chen, Yousheng; Zhang, Zongping; Chen, Yan; Zhang, Weifeng

2017-08-01

This paper proposed a novel speech processing algorithm in cochlear implant, which used harmonicity cues to enhance tonal information in Mandarin Chinese speech recognition. The input speech was filtered by a 4-channel band-pass filter bank. The frequency ranges for the four bands were: 300-621, 621-1285, 1285-2657, and 2657-5499 Hz. In each pass band, temporal envelope and periodicity cues (TEPCs) below 400 Hz were extracted by full wave rectification and low-pass filtering. The TEPCs were modulated by a sinusoidal carrier, the frequency of which was fundamental frequency (F0) and its harmonics most close to the center frequency of each band. Signals from each band were combined together to obtain an output speech. Mandarin tone, word, and sentence recognition in quiet listening conditions were tested for the extensively used continuous interleaved sampling (CIS) strategy and the novel F0-harmonic algorithm. Results found that the F0-harmonic algorithm performed consistently better than CIS strategy in Mandarin tone, word, and sentence recognition. In addition, sentence recognition rate was higher than word recognition rate, as a result of contextual information in the sentence. Moreover, tone 3 and 4 performed better than tone 1 and tone 2, due to the easily identified features of the former. In conclusion, the F0-harmonic algorithm could enhance tonal information in cochlear implant speech processing due to the use of harmonicity cues, thereby improving Mandarin tone, word, and sentence recognition. Further study will focus on the test of the F0-harmonic algorithm in noisy listening conditions.

Speech recognition in one- and two-talker maskers in school-age children and adults: Development of perceptual masking and glimpsing

PubMed Central

Buss, Emily; Leibold, Lori J.; Porter, Heather L.; Grose, John H.

2017-01-01

Children perform more poorly than adults on a wide range of masked speech perception paradigms, but this effect is particularly pronounced when the masker itself is also composed of speech. The present study evaluated two factors that might contribute to this effect: the ability to perceptually isolate the target from masker speech, and the ability to recognize target speech based on sparse cues (glimpsing). Speech reception thresholds (SRTs) were estimated for closed-set, disyllabic word recognition in children (5–16 years) and adults in a one- or two-talker masker. Speech maskers were 60 dB sound pressure level (SPL), and they were either presented alone or in combination with a 50-dB-SPL speech-shaped noise masker. There was an age effect overall, but performance was adult-like at a younger age for the one-talker than the two-talker masker. Noise tended to elevate SRTs, particularly for older children and adults, and when summed with the one-talker masker. Removing time-frequency epochs associated with a poor target-to-masker ratio markedly improved SRTs, with larger effects for younger listeners; the age effect was not eliminated, however. Results were interpreted as indicating that development of speech-in-speech recognition is likely impacted by development of both perceptual masking and the ability recognize speech based on sparse cues. PMID:28464682

Speech fluency profile on different tasks for individuals with Parkinson's disease.

PubMed

Juste, Fabiola Staróbole; Andrade, Claudia Regina Furquim de

2017-07-20

To characterize the speech fluency profile of patients with Parkinson's disease. Study participants were 40 individuals of both genders aged 40 to 80 years divided into 2 groups: Research Group - RG (20 individuals with diagnosis of Parkinson's disease) and Control Group - CG (20 individuals with no communication or neurological disorders). For all of the participants, three speech samples involving different tasks were collected: monologue, individual reading, and automatic speech. The RG presented a significant larger number of speech disruptions, both stuttering-like and typical dysfluencies, and higher percentage of speech discontinuity in the monologue and individual reading tasks compared with the CG. Both groups presented reduced number of speech disruptions (stuttering-like and typical dysfluencies) in the automatic speech task; the groups presented similar performance in this task. Regarding speech rate, individuals in the RG presented lower number of words and syllables per minute compared with those in the CG in all speech tasks. Participants of the RG presented altered parameters of speech fluency compared with those of the CG; however, this change in fluency cannot be considered a stuttering disorder.

Working memory capacity may influence perceived effort during aided speech recognition in noise.

PubMed

Rudner, Mary; Lunner, Thomas; Behrens, Thomas; Thorén, Elisabet Sundewall; Rönnberg, Jerker

2012-09-01

Recently there has been interest in using subjective ratings as a measure of perceived effort during speech recognition in noise. Perceived effort may be an indicator of cognitive load. Thus, subjective effort ratings during speech recognition in noise may covary both with signal-to-noise ratio (SNR) and individual cognitive capacity. The present study investigated the relation between subjective ratings of the effort involved in listening to speech in noise, speech recognition performance, and individual working memory (WM) capacity in hearing impaired hearing aid users. In two experiments, participants with hearing loss rated perceived effort during aided speech perception in noise. Noise type and SNR were manipulated in both experiments, and in the second experiment hearing aid compression release settings were also manipulated. Speech recognition performance was measured along with WM capacity. There were 46 participants in all with bilateral mild to moderate sloping hearing loss. In Experiment 1 there were 16 native Danish speakers (eight women and eight men) with a mean age of 63.5 yr (SD = 12.1) and average pure tone (PT) threshold of 47. 6 dB (SD = 9.8). In Experiment 2 there were 30 native Swedish speakers (19 women and 11 men) with a mean age of 70 yr (SD = 7.8) and average PT threshold of 45.8 dB (SD = 6.6). A visual analog scale (VAS) was used for effort rating in both experiments. In Experiment 1, effort was rated at individually adapted SNRs while in Experiment 2 it was rated at fixed SNRs. Speech recognition in noise performance was measured using adaptive procedures in both experiments with Dantale II sentences in Experiment 1 and Hagerman sentences in Experiment 2. WM capacity was measured using a letter-monitoring task in Experiment 1 and the reading span task in Experiment 2. In both experiments, there was a strong and significant relation between rated effort and SNR that was independent of individual WM capacity, whereas the relation between rated effort and noise type seemed to be influenced by individual WM capacity. Experiment 2 showed that hearing aid compression setting influenced rated effort. Subjective ratings of the effort involved in speech recognition in noise reflect SNRs, and individual cognitive capacity seems to influence relative rating of noise type. American Academy of Audiology.

Blind speech separation system for humanoid robot with FastICA for audio filtering and separation

NASA Astrophysics Data System (ADS)

Budiharto, Widodo; Santoso Gunawan, Alexander Agung

2016-07-01

Nowadays, there are many developments in building intelligent humanoid robot, mainly in order to handle voice and image. In this research, we propose blind speech separation system using FastICA for audio filtering and separation that can be used in education or entertainment. Our main problem is to separate the multi speech sources and also to filter irrelevant noises. After speech separation step, the results will be integrated with our previous speech and face recognition system which is based on Bioloid GP robot and Raspberry Pi 2 as controller. The experimental results show the accuracy of our blind speech separation system is about 88% in command and query recognition cases.

New Ideas for Speech Recognition and Related Technologies

DOE Office of Scientific and Technical Information (OSTI.GOV)

Holzrichter, J F

The ideas relating to the use of organ motion sensors for the purposes of speech recognition were first described by.the author in spring 1994. During the past year, a series of productive collaborations between the author, Tom McEwan and Larry Ng ensued and have lead to demonstrations, new sensor ideas, and algorithmic descriptions of a large number of speech recognition concepts. This document summarizes the basic concepts of recognizing speech once organ motions have been obtained. Micro power radars and their uses for the measurement of body organ motions, such as those of the heart and lungs, have been demonstratedmore » by Tom McEwan over the past two years. McEwan and I conducted a series of experiments, using these instruments, on vocal organ motions beginning in late spring, during which we observed motions of vocal folds (i.e., cords), tongue, jaw, and related organs that are very useful for speech recognition and other purposes. These will be reviewed in a separate paper. Since late summer 1994, Lawrence Ng and I have worked to make many of the initial recognition ideas more rigorous and to investigate the applications of these new ideas to new speech recognition algorithms, to speech coding, and to speech synthesis. I introduce some of those ideas in section IV of this document, and we describe them more completely in the document following this one, UCRL-UR-120311. For the design and operation of micro-power radars and their application to body organ motions, the reader may contact Tom McEwan directly. The capability for using EM sensors (i.e., radar units) to measure body organ motions and positions has been available for decades. Impediments to their use appear to have been size, excessive power, lack of resolution, and lack of understanding of the value of organ motion measurements, especially as applied to speech related technologies. However, with the invention of very low power, portable systems as demonstrated by McEwan at LLNL researchers have begun to think differently about practical applications of such radars. In particular, his demonstrations of heart and lung motions have opened up many new areas of application for human and animal measurements.« less

The effect of sensorineural hearing loss and tinnitus on speech recognition over air and bone conduction military communications headsets.

PubMed

Manning, Candice; Mermagen, Timothy; Scharine, Angelique

2017-06-01

Military personnel are at risk for hearing loss due to noise exposure during deployment (USACHPPM, 2008). Despite mandated use of hearing protection, hearing loss and tinnitus are prevalent due to reluctance to use hearing protection. Bone conduction headsets can offer good speech intelligibility for normal hearing (NH) listeners while allowing the ears to remain open in quiet environments and the use of hearing protection when needed. Those who suffer from tinnitus, the experience of perceiving a sound not produced by an external source, often show degraded speech recognition; however, it is unclear whether this is a result of decreased hearing sensitivity or increased distractibility (Moon et al., 2015). It has been suggested that the vibratory stimulation of a bone conduction headset might ameliorate the effects of tinnitus on speech perception; however, there is currently no research to support or refute this claim (Hoare et al., 2014). Speech recognition of words presented over air conduction and bone conduction headsets was measured for three groups of listeners: NH, sensorineural hearing impaired, and/or tinnitus sufferers. Three levels of speech-to-noise (SNR = 0, -6, -12 dB) were created by embedding speech items in pink noise. Better speech recognition performance was observed with the bone conduction headset regardless of hearing profile, and speech intelligibility was a function of SNR. Discussion will include study limitations and the implications of these findings for those serving in the military. Published by Elsevier B.V.

Speaker normalization for chinese vowel recognition in cochlear implants.

PubMed

Luo, Xin; Fu, Qian-Jie

2005-07-01

Because of the limited spectra-temporal resolution associated with cochlear implants, implant patients often have greater difficulty with multitalker speech recognition. The present study investigated whether multitalker speech recognition can be improved by applying speaker normalization techniques to cochlear implant speech processing. Multitalker Chinese vowel recognition was tested with normal-hearing Chinese-speaking subjects listening to a 4-channel cochlear implant simulation, with and without speaker normalization. For each subject, speaker normalization was referenced to the speaker that produced the best recognition performance under conditions without speaker normalization. To match the remaining speakers to this "optimal" output pattern, the overall frequency range of the analysis filter bank was adjusted for each speaker according to the ratio of the mean third formant frequency values between the specific speaker and the reference speaker. Results showed that speaker normalization provided a small but significant improvement in subjects' overall recognition performance. After speaker normalization, subjects' patterns of recognition performance across speakers changed, demonstrating the potential for speaker-dependent effects with the proposed normalization technique.

Speech Perception, Word Recognition and the Structure of the Lexicon. Research on Speech Perception Progress Report No. 10.

ERIC Educational Resources Information Center

Pisoni, David B.; And Others

The results of three projects concerned with auditory word recognition and the structure of the lexicon are reported in this paper. The first project described was designed to test experimentally several specific predictions derived from MACS, a simulation model of the Cohort Theory of word recognition. The second project description provides the…

The Development of the Orthographic Consistency Effect in Speech Recognition: From Sublexical to Lexical Involvement

ERIC Educational Resources Information Center

Ventura, Paulo; Morais, Jose; Kolinsky, Regine

2007-01-01

The influence of orthography on children's on-line auditory word recognition was studied from the end of Grade 2 to the end of Grade 4, by examining the orthographic consistency effect [Ziegler, J. C., & Ferrand, L. (1998). Orthography shapes the perception of speech: The consistency effect in auditory recognition. "Psychonomic Bulletin & Review",…

A novel method of language modeling for automatic captioning in TC video teleconferencing.

PubMed

Zhang, Xiaojia; Zhao, Yunxin; Schopp, Laura

2007-05-01

We are developing an automatic captioning system for teleconsultation video teleconferencing (TC-VTC) in telemedicine, based on large vocabulary conversational speech recognition. In TC-VTC, doctors' speech contains a large number of infrequently used medical terms in spontaneous styles. Due to insufficiency of data, we adopted mixture language modeling, with models trained from several datasets of medical and nonmedical domains. This paper proposes novel modeling and estimation methods for the mixture language model (LM). Component LMs are trained from individual datasets, with class n-gram LMs trained from in-domain datasets and word n-gram LMs trained from out-of-domain datasets, and they are interpolated into a mixture LM. For class LMs, semantic categories are used for class definition on medical terms, names, and digits. The interpolation weights of a mixture LM are estimated by a greedy algorithm of forward weight adjustment (FWA). The proposed mixing of in-domain class LMs and out-of-domain word LMs, the semantic definitions of word classes, as well as the weight-estimation algorithm of FWA are effective on the TC-VTC task. As compared with using mixtures of word LMs with weights estimated by the conventional expectation-maximization algorithm, the proposed methods led to a 21% reduction of perplexity on test sets of five doctors, which translated into improvements of captioning accuracy.

Do What I Say! Voice Recognition Makes Major Advances.

ERIC Educational Resources Information Center

Ruley, C. Dorsey

1994-01-01

Explains voice recognition technology applications in the workplace, schools, and libraries. Highlights include a voice-controlled work station using the DragonDictate system that can be used with dyslexic students, converting text to speech, and converting speech to text. (LRW)

Emotional recognition from the speech signal for a virtual education agent

NASA Astrophysics Data System (ADS)

Tickle, A.; Raghu, S.; Elshaw, M.

2013-06-01

This paper explores the extraction of features from the speech wave to perform intelligent emotion recognition. A feature extract tool (openSmile) was used to obtain a baseline set of 998 acoustic features from a set of emotional speech recordings from a microphone. The initial features were reduced to the most important ones so recognition of emotions using a supervised neural network could be performed. Given that the future use of virtual education agents lies with making the agents more interactive, developing agents with the capability to recognise and adapt to the emotional state of humans is an important step.

Robotics control using isolated word recognition of voice input

NASA Technical Reports Server (NTRS)

Weiner, J. M.

1977-01-01

A speech input/output system is presented that can be used to communicate with a task oriented system. Human speech commands and synthesized voice output extend conventional information exchange capabilities between man and machine by utilizing audio input and output channels. The speech input facility is comprised of a hardware feature extractor and a microprocessor implemented isolated word or phrase recognition system. The recognizer offers a medium sized (100 commands), syntactically constrained vocabulary, and exhibits close to real time performance. The major portion of the recognition processing required is accomplished through software, minimizing the complexity of the hardware feature extractor.

Measuring the effects of spectral smearing and enhancement on speech recognition in noise for adults and children

PubMed Central

Nittrouer, Susan; Tarr, Eric; Wucinich, Taylor; Moberly, Aaron C.; Lowenstein, Joanna H.

2015-01-01

Broadened auditory filters associated with sensorineural hearing loss have clearly been shown to diminish speech recognition in noise for adults, but far less is known about potential effects for children. This study examined speech recognition in noise for adults and children using simulated auditory filters of different widths. Specifically, 5 groups (20 listeners each) of adults or children (5 and 7 yrs), were asked to recognize sentences in speech-shaped noise. Seven-year-olds listened at 0 dB signal-to-noise ratio (SNR) only; 5-yr-olds listened at +3 or 0 dB SNR; and adults listened at 0 or −3 dB SNR. Sentence materials were processed both to smear the speech spectrum (i.e., simulate broadened filters), and to enhance the spectrum (i.e., simulate narrowed filters). Results showed: (1) Spectral smearing diminished recognition for listeners of all ages; (2) spectral enhancement did not improve recognition, and in fact diminished it somewhat; and (3) interactions were observed between smearing and SNR, but only for adults. That interaction made age effects difficult to gauge. Nonetheless, it was concluded that efforts to diagnose the extent of broadening of auditory filters and to develop techniques to correct this condition could benefit patients with hearing loss, especially children. PMID:25920851

A longitudinal study of the bilateral benefit in children with bilateral cochlear implants.

PubMed

Asp, Filip; Mäki-Torkko, Elina; Karltorp, Eva; Harder, Henrik; Hergils, Leif; Eskilsson, Gunnar; Stenfelt, Stefan

2015-02-01

To study the development of the bilateral benefit in children using bilateral cochlear implants by measurements of speech recognition and sound localization. Bilateral and unilateral speech recognition in quiet, in multi-source noise, and horizontal sound localization was measured at three occasions during a two-year period, without controlling for age or implant experience. Longitudinal and cross-sectional analyses were performed. Results were compared to cross-sectional data from children with normal hearing. Seventy-eight children aged 5.1-11.9 years, with a mean bilateral cochlear implant experience of 3.3 years and a mean age of 7.8 years, at inclusion in the study. Thirty children with normal hearing aged 4.8-9.0 years provided normative data. For children with cochlear implants, bilateral and unilateral speech recognition in quiet was comparable whereas a bilateral benefit for speech recognition in noise and sound localization was found at all three test occasions. Absolute performance was lower than in children with normal hearing. Early bilateral implantation facilitated sound localization. A bilateral benefit for speech recognition in noise and sound localization continues to exist over time for children with bilateral cochlear implants, but no relative improvement is found after three years of bilateral cochlear implant experience.

Phonological mismatch makes aided speech recognition in noise cognitively taxing.

PubMed

Rudner, Mary; Foo, Catharina; Rönnberg, Jerker; Lunner, Thomas

2007-12-01

The working memory framework for Ease of Language Understanding predicts that speech processing becomes more effortful, thus requiring more explicit cognitive resources, when there is mismatch between speech input and phonological representations in long-term memory. To test this prediction, we changed the compression release settings in the hearing instruments of experienced users and allowed them to train for 9 weeks with the new settings. After training, aided speech recognition in noise was tested with both the trained settings and orthogonal settings. We postulated that training would lead to acclimatization to the trained setting, which in turn would involve establishment of new phonological representations in long-term memory. Further, we postulated that after training, testing with orthogonal settings would give rise to phonological mismatch, associated with more explicit cognitive processing. Thirty-two participants (mean=70.3 years, SD=7.7) with bilateral sensorineural hearing loss (pure-tone average=46.0 dB HL, SD=6.5), bilaterally fitted for more than 1 year with digital, two-channel, nonlinear signal processing hearing instruments and chosen from the patient population at the Linköping University Hospital were randomly assigned to 9 weeks training with new, fast (40 ms) or slow (640 ms), compression release settings in both channels. Aided speech recognition in noise performance was tested according to a design with three within-group factors: test occasion (T1, T2), test setting (fast, slow), and type of noise (unmodulated, modulated) and one between-group factor: experience setting (fast, slow) for two types of speech materials-the highly constrained Hagerman sentences and the less-predictable Hearing in Noise Test (HINT). Complex cognitive capacity was measured using the reading span and letter monitoring tests. PREDICTION: We predicted that speech recognition in noise at T2 with mismatched experience and test settings would be associated with more explicit cognitive processing and thus stronger correlations with complex cognitive measures, as well as poorer performance if complex cognitive capacity was exceeded. Under mismatch conditions, stronger correlations were found between performance on speech recognition with the Hagerman sentences and reading span, along with poorer speech recognition for participants with low reading span scores. No consistent mismatch effect was found with HINT. The mismatch prediction generated by the working memory framework for Ease of Language Understanding is supported for speech recognition in noise with the highly constrained Hagerman sentences but not the less-predictable HINT.

The performance of an automatic acoustic-based program classifier compared to hearing aid users' manual selection of listening programs.

PubMed

Searchfield, Grant D; Linford, Tania; Kobayashi, Kei; Crowhen, David; Latzel, Matthias

2018-03-01

To compare preference for and performance of manually selected programmes to an automatic sound classifier, the Phonak AutoSense OS. A single blind repeated measures study. Participants were fit with Phonak Virto V90 ITE aids; preferences for different listening programmes were compared across four different sound scenarios (speech in: quiet, noise, loud noise and a car). Following a 4-week trial preferences were reassessed and the users preferred programme was compared to the automatic classifier for sound quality and hearing in noise (HINT test) using a 12 loudspeaker array. Twenty-five participants with symmetrical moderate-severe sensorineural hearing loss. Participant preferences of manual programme for scenarios varied considerably between and within sessions. A HINT Speech Reception Threshold (SRT) advantage was observed for the automatic classifier over participant's manual selection for speech in quiet, loud noise and car noise. Sound quality ratings were similar for both manual and automatic selections. The use of a sound classifier is a viable alternative to manual programme selection.

Practical automatic Arabic license plate recognition system

NASA Astrophysics Data System (ADS)

Mohammad, Khader; Agaian, Sos; Saleh, Hani

2011-02-01

Since 1970's, the need of an automatic license plate recognition system, sometimes referred as Automatic License Plate Recognition system, has been increasing. A license plate recognition system is an automatic system that is able to recognize a license plate number, extracted from image sensors. In specific, Automatic License Plate Recognition systems are being used in conjunction with various transportation systems in application areas such as law enforcement (e.g. speed limit enforcement) and commercial usages such as parking enforcement and automatic toll payment private and public entrances, border control, theft and vandalism control. Vehicle license plate recognition has been intensively studied in many countries. Due to the different types of license plates being used, the requirement of an automatic license plate recognition system is different for each country. [License plate detection using cluster run length smoothing algorithm ].Generally, an automatic license plate localization and recognition system is made up of three modules; license plate localization, character segmentation and optical character recognition modules. This paper presents an Arabic license plate recognition system that is insensitive to character size, font, shape and orientation with extremely high accuracy rate. The proposed system is based on a combination of enhancement, license plate localization, morphological processing, and feature vector extraction using the Haar transform. The performance of the system is fast due to classification of alphabet and numerals based on the license plate organization. Experimental results for license plates of two different Arab countries show an average of 99 % successful license plate localization and recognition in a total of more than 20 different images captured from a complex outdoor environment. The results run times takes less time compared to conventional and many states of art methods.

Inter-speaker speech variability assessment using statistical deformable models from 3.0 tesla magnetic resonance images.

PubMed

Vasconcelos, Maria J M; Ventura, Sandra M R; Freitas, Diamantino R S; Tavares, João Manuel R S

2012-03-01

The morphological and dynamic characterisation of the vocal tract during speech production has been gaining greater attention due to the motivation of the latest improvements in magnetic resonance (MR) imaging; namely, with the use of higher magnetic fields, such as 3.0 Tesla. In this work, the automatic study of the vocal tract from 3.0 Tesla MR images was assessed through the application of statistical deformable models. Therefore, the primary goal focused on the analysis of the shape of the vocal tract during the articulation of European Portuguese sounds, followed by the evaluation of the results concerning the automatic segmentation, i.e. identification of the vocal tract in new MR images. In what concerns speech production, this is the first attempt to automatically characterise and reconstruct the vocal tract shape of 3.0 Tesla MR images by using deformable models; particularly, by using active and appearance shape models. The achieved results clearly evidence the adequacy and advantage of the automatic analysis of the 3.0 Tesla MR images of these deformable models in order to extract the vocal tract shape and assess the involved articulatory movements. These achievements are mostly required, for example, for a better knowledge of speech production, mainly of patients suffering from articulatory disorders, and to build enhanced speech synthesizer models.

Improving language models for radiology speech recognition.

PubMed

Paulett, John M; Langlotz, Curtis P

2009-02-01

Speech recognition systems have become increasingly popular as a means to produce radiology reports, for reasons both of efficiency and of cost. However, the suboptimal recognition accuracy of these systems can affect the productivity of the radiologists creating the text reports. We analyzed a database of over two million de-identified radiology reports to determine the strongest determinants of word frequency. Our results showed that body site and imaging modality had a similar influence on the frequency of words and of three-word phrases as did the identity of the speaker. These findings suggest that the accuracy of speech recognition systems could be significantly enhanced by further tailoring their language models to body site and imaging modality, which are readily available at the time of report creation.

Connected word recognition using a cascaded neuro-computational model

NASA Astrophysics Data System (ADS)

Hoya, Tetsuya; van Leeuwen, Cees

2016-10-01

We propose a novel framework for processing a continuous speech stream that contains a varying number of words, as well as non-speech periods. Speech samples are segmented into word-tokens and non-speech periods. An augmented version of an earlier-proposed, cascaded neuro-computational model is used for recognising individual words within the stream. Simulation studies using both a multi-speaker-dependent and speaker-independent digit string database show that the proposed method yields a recognition performance comparable to that obtained by a benchmark approach using hidden Markov models with embedded training.

Cognitive Predictors of Spoken Word Recognition in Children With and Without Developmental Language Disorders.

PubMed

Evans, Julia L; Gillam, Ronald B; Montgomery, James W

2018-05-10

This study examined the influence of cognitive factors on spoken word recognition in children with developmental language disorder (DLD) and typically developing (TD) children. Participants included 234 children (aged 7;0-11;11 years;months), 117 with DLD and 117 TD children, propensity matched for age, gender, socioeconomic status, and maternal education. Children completed a series of standardized assessment measures, a forward gating task, a rapid automatic naming task, and a series of tasks designed to examine cognitive factors hypothesized to influence spoken word recognition including phonological working memory, updating, attention shifting, and interference inhibition. Spoken word recognition for both initial and final accept gate points did not differ for children with DLD and TD controls after controlling target word knowledge in both groups. The 2 groups also did not differ on measures of updating, attention switching, and interference inhibition. Despite the lack of difference on these measures, for children with DLD, attention shifting and interference inhibition were significant predictors of spoken word recognition, whereas updating and receptive vocabulary were significant predictors of speed of spoken word recognition for the children in the TD group. Contrary to expectations, after controlling for target word knowledge, spoken word recognition did not differ for children with DLD and TD controls; however, the cognitive processing factors that influenced children's ability to recognize the target word in a stream of speech differed qualitatively for children with and without DLDs.

An analysis of the influence of deep neural network (DNN) topology in bottleneck feature based language recognition.

PubMed

Lozano-Diez, Alicia; Zazo, Ruben; Toledano, Doroteo T; Gonzalez-Rodriguez, Joaquin

2017-01-01

Language recognition systems based on bottleneck features have recently become the state-of-the-art in this research field, showing its success in the last Language Recognition Evaluation (LRE 2015) organized by NIST (U.S. National Institute of Standards and Technology). This type of system is based on a deep neural network (DNN) trained to discriminate between phonetic units, i.e. trained for the task of automatic speech recognition (ASR). This DNN aims to compress information in one of its layers, known as bottleneck (BN) layer, which is used to obtain a new frame representation of the audio signal. This representation has been proven to be useful for the task of language identification (LID). Thus, bottleneck features are used as input to the language recognition system, instead of a classical parameterization of the signal based on cepstral feature vectors such as MFCCs (Mel Frequency Cepstral Coefficients). Despite the success of this approach in language recognition, there is a lack of studies analyzing in a systematic way how the topology of the DNN influences the performance of bottleneck feature-based language recognition systems. In this work, we try to fill-in this gap, analyzing language recognition results with different topologies for the DNN used to extract the bottleneck features, comparing them and against a reference system based on a more classical cepstral representation of the input signal with a total variability model. This way, we obtain useful knowledge about how the DNN configuration influences bottleneck feature-based language recognition systems performance.

Measuring listening effort: driving simulator vs. simple dual-task paradigm

PubMed Central

Wu, Yu-Hsiang; Aksan, Nazan; Rizzo, Matthew; Stangl, Elizabeth; Zhang, Xuyang; Bentler, Ruth

2014-01-01

Objectives The dual-task paradigm has been widely used to measure listening effort. The primary objectives of the study were to (1) investigate the effect of hearing aid amplification and a hearing aid directional technology on listening effort measured by a complicated, more real world dual-task paradigm, and (2) compare the results obtained with this paradigm to a simpler laboratory-style dual-task paradigm. Design The listening effort of adults with hearing impairment was measured using two dual-task paradigms, wherein participants performed a speech recognition task simultaneously with either a driving task in a simulator or a visual reaction-time task in a sound-treated booth. The speech materials and road noises for the speech recognition task were recorded in a van traveling on the highway in three hearing aid conditions: unaided, aided with omni directional processing (OMNI), and aided with directional processing (DIR). The change in the driving task or the visual reaction-time task performance across the conditions quantified the change in listening effort. Results Compared to the driving-only condition, driving performance declined significantly with the addition of the speech recognition task. Although the speech recognition score was higher in the OMNI and DIR conditions than in the unaided condition, driving performance was similar across these three conditions, suggesting that listening effort was not affected by amplification and directional processing. Results from the simple dual-task paradigm showed a similar trend: hearing aid technologies improved speech recognition performance, but did not affect performance in the visual reaction-time task (i.e., reduce listening effort). The correlation between listening effort measured using the driving paradigm and the visual reaction-time task paradigm was significant. The finding showing that our older (56 to 85 years old) participants’ better speech recognition performance did not result in reduced listening effort was not consistent with literature that evaluated younger (approximately 20 years old), normal hearing adults. Because of this, a follow-up study was conducted. In the follow-up study, the visual reaction-time dual-task experiment using the same speech materials and road noises was repeated on younger adults with normal hearing. Contrary to findings with older participants, the results indicated that the directional technology significantly improved performance in both speech recognition and visual reaction-time tasks. Conclusions Adding a speech listening task to driving undermined driving performance. Hearing aid technologies significantly improved speech recognition while driving, but did not significantly reduce listening effort. Listening effort measured by dual-task experiments using a simulated real-world driving task and a conventional laboratory-style task was generally consistent. For a given listening environment, the benefit of hearing aid technologies on listening effort measured from younger adults with normal hearing may not be fully translated to older listeners with hearing impairment. PMID:25083599

Speech recognition: Acoustic-phonetic knowledge acquisition and representation

NASA Astrophysics Data System (ADS)

Zue, Victor W.

1988-09-01

The long-term research goal is to develop and implement speaker-independent continuous speech recognition systems. It is believed that the proper utilization of speech-specific knowledge is essential for such advanced systems. This research is thus directed toward the acquisition, quantification, and representation, of acoustic-phonetic and lexical knowledge, and the application of this knowledge to speech recognition algorithms. In addition, we are exploring new speech recognition alternatives based on artificial intelligence and connectionist techniques. We developed a statistical model for predicting the acoustic realization of stop consonants in various positions in the syllable template. A unification-based grammatical formalism was developed for incorporating this model into the lexical access algorithm. We provided an information-theoretic justification for the hierarchical structure of the syllable template. We analyzed segmented duration for vowels and fricatives in continuous speech. Based on contextual information, we developed durational models for vowels and fricatives that account for over 70 percent of the variance, using data from multiple, unknown speakers. We rigorously evaluated the ability of human spectrogram readers to identify stop consonants spoken by many talkers and in a variety of phonetic contexts. Incorporating the declarative knowledge used by the readers, we developed a knowledge-based system for stop identification. We achieved comparable system performance to that to the readers.

Across-site patterns of modulation detection: Relation to speech recognitiona)

PubMed Central

Garadat, Soha N.; Zwolan, Teresa A.; Pfingst, Bryan E.

2012-01-01

The aim of this study was to identify across-site patterns of modulation detection thresholds (MDTs) in subjects with cochlear implants and to determine if removal of sites with the poorest MDTs from speech processor programs would result in improved speech recognition. Five hundred millisecond trains of symmetric-biphasic pulses were modulated sinusoidally at 10 Hz and presented at a rate of 900 pps using monopolar stimulation. Subjects were asked to discriminate a modulated pulse train from an unmodulated pulse train for all electrodes in quiet and in the presence of an interleaved unmodulated masker presented on the adjacent site. Across-site patterns of masked MDTs were then used to construct two 10-channel MAPs such that one MAP consisted of sites with the best masked MDTs and the other MAP consisted of sites with the worst masked MDTs. Subjects’ speech recognition skills were compared when they used these two different MAPs. Results showed that MDTs were variable across sites and were elevated in the presence of a masker by various amounts across sites. Better speech recognition was observed when the processor MAP consisted of sites with best masked MDTs, suggesting that temporal modulation sensitivity has important contributions to speech recognition with a cochlear implant. PMID:22559376

Advances to the development of a basic Mexican sign-to-speech and text language translator

NASA Astrophysics Data System (ADS)

Garcia-Bautista, G.; Trujillo-Romero, F.; Diaz-Gonzalez, G.

2016-09-01

Sign Language (SL) is the basic alternative communication method between deaf people. However, most of the hearing people have trouble understanding the SL, making communication with deaf people almost impossible and taking them apart from daily activities. In this work we present an automatic basic real-time sign language translator capable of recognize a basic list of Mexican Sign Language (MSL) signs of 10 meaningful words, letters (A-Z) and numbers (1-10) and translate them into speech and text. The signs were collected from a group of 35 MSL signers executed in front of a Microsoft Kinect™ Sensor. The hand gesture recognition system use the RGB-D camera to build and storage data point clouds, color and skeleton tracking information. In this work we propose a method to obtain the representative hand trajectory pattern information. We use Euclidean Segmentation method to obtain the hand shape and Hierarchical Centroid as feature extraction method for images of numbers and letters. A pattern recognition method based on a Back Propagation Artificial Neural Network (ANN) is used to interpret the hand gestures. Finally, we use K-Fold Cross Validation method for training and testing stages. Our results achieve an accuracy of 95.71% on words, 98.57% on numbers and 79.71% on letters. In addition, an interactive user interface was designed to present the results in voice and text format.

Science 101: How Does Speech-Recognition Software Work?

ERIC Educational Resources Information Center

Robertson, Bill

2016-01-01

This column provides background science information for elementary teachers. Many innovations with computer software begin with analysis of how humans do a task. This article takes a look at how humans recognize spoken words and explains the origins of speech-recognition software.

Speech Intelligibility Predicted from Neural Entrainment of the Speech Envelope.

PubMed

Vanthornhout, Jonas; Decruy, Lien; Wouters, Jan; Simon, Jonathan Z; Francart, Tom

2018-04-01

Speech intelligibility is currently measured by scoring how well a person can identify a speech signal. The results of such behavioral measures reflect neural processing of the speech signal, but are also influenced by language processing, motivation, and memory. Very often, electrophysiological measures of hearing give insight in the neural processing of sound. However, in most methods, non-speech stimuli are used, making it hard to relate the results to behavioral measures of speech intelligibility. The use of natural running speech as a stimulus in electrophysiological measures of hearing is a paradigm shift which allows to bridge the gap between behavioral and electrophysiological measures. Here, by decoding the speech envelope from the electroencephalogram, and correlating it with the stimulus envelope, we demonstrate an electrophysiological measure of neural processing of running speech. We show that behaviorally measured speech intelligibility is strongly correlated with our electrophysiological measure. Our results pave the way towards an objective and automatic way of assessing neural processing of speech presented through auditory prostheses, reducing confounds such as attention and cognitive capabilities. We anticipate that our electrophysiological measure will allow better differential diagnosis of the auditory system, and will allow the development of closed-loop auditory prostheses that automatically adapt to individual users.

Watch what you say, your computer might be listening: A review of automated speech recognition

NASA Technical Reports Server (NTRS)

Degennaro, Stephen V.

1991-01-01

Spoken language is the most convenient and natural means by which people interact with each other and is, therefore, a promising candidate for human-machine interactions. Speech also offers an additional channel for hands-busy applications, complementing the use of motor output channels for control. Current speech recognition systems vary considerably across a number of important characteristics, including vocabulary size, speaking mode, training requirements for new speakers, robustness to acoustic environments, and accuracy. Algorithmically, these systems range from rule-based techniques through more probabilistic or self-learning approaches such as hidden Markov modeling and neural networks. This tutorial begins with a brief summary of the relevant features of current speech recognition systems and the strengths and weaknesses of the various algorithmic approaches.

Some Neurocognitive Correlates of Noise-Vocoded Speech Perception in Children With Normal Hearing: A Replication and Extension of ).

PubMed

Roman, Adrienne S; Pisoni, David B; Kronenberger, William G; Faulkner, Kathleen F

Noise-vocoded speech is a valuable research tool for testing experimental hypotheses about the effects of spectral degradation on speech recognition in adults with normal hearing (NH). However, very little research has utilized noise-vocoded speech with children with NH. Earlier studies with children with NH focused primarily on the amount of spectral information needed for speech recognition without assessing the contribution of neurocognitive processes to speech perception and spoken word recognition. In this study, we first replicated the seminal findings reported by ) who investigated effects of lexical density and word frequency on noise-vocoded speech perception in a small group of children with NH. We then extended the research to investigate relations between noise-vocoded speech recognition abilities and five neurocognitive measures: auditory attention (AA) and response set, talker discrimination, and verbal and nonverbal short-term working memory. Thirty-one children with NH between 5 and 13 years of age were assessed on their ability to perceive lexically controlled words in isolation and in sentences that were noise-vocoded to four spectral channels. Children were also administered vocabulary assessments (Peabody Picture Vocabulary test-4th Edition and Expressive Vocabulary test-2nd Edition) and measures of AA (NEPSY AA and response set and a talker discrimination task) and short-term memory (visual digit and symbol spans). Consistent with the findings reported in the original ) study, we found that children perceived noise-vocoded lexically easy words better than lexically hard words. Words in sentences were also recognized better than the same words presented in isolation. No significant correlations were observed between noise-vocoded speech recognition scores and the Peabody Picture Vocabulary test-4th Edition using language quotients to control for age effects. However, children who scored higher on the Expressive Vocabulary test-2nd Edition recognized lexically easy words better than lexically hard words in sentences. Older children perceived noise-vocoded speech better than younger children. Finally, we found that measures of AA and short-term memory capacity were significantly correlated with a child's ability to perceive noise-vocoded isolated words and sentences. First, we successfully replicated the major findings from the ) study. Because familiarity, phonological distinctiveness and lexical competition affect word recognition, these findings provide additional support for the proposal that several foundational elementary neurocognitive processes underlie the perception of spectrally degraded speech. Second, we found strong and significant correlations between performance on neurocognitive measures and children's ability to recognize words and sentences noise-vocoded to four spectral channels. These findings extend earlier research suggesting that perception of spectrally degraded speech reflects early peripheral auditory processes, as well as additional contributions of executive function, specifically, selective attention and short-term memory processes in spoken word recognition. The present findings suggest that AA and short-term memory support robust spoken word recognition in children with NH even under compromised and challenging listening conditions. These results are relevant to research carried out with listeners who have hearing loss, because they are routinely required to encode, process, and understand spectrally degraded acoustic signals.

Some Neurocognitive Correlates of Noise-Vocoded Speech Perception in Children with Normal Hearing: A Replication and Extension of Eisenberg et al., 2002

PubMed Central

Roman, Adrienne S.; Pisoni, David B.; Kronenberger, William G.; Faulkner, Kathleen F.

2016-01-01

Objectives Noise-vocoded speech is a valuable research tool for testing experimental hypotheses about the effects of spectral-degradation on speech recognition in adults with normal hearing (NH). However, very little research has utilized noise-vocoded speech with children with NH. Earlier studies with children with NH focused primarily on the amount of spectral information needed for speech recognition without assessing the contribution of neurocognitive processes to speech perception and spoken word recognition. In this study, we first replicated the seminal findings reported by Eisenberg et al. (2002) who investigated effects of lexical density and word frequency on noise-vocoded speech perception in a small group of children with NH. We then extended the research to investigate relations between noise-vocoded speech recognition abilities and five neurocognitive measures: auditory attention and response set, talker discrimination and verbal and nonverbal short-term working memory. Design Thirty-one children with NH between 5 and 13 years of age were assessed on their ability to perceive lexically controlled words in isolation and in sentences that were noise-vocoded to four spectral channels. Children were also administered vocabulary assessments (PPVT-4 and EVT-2) and measures of auditory attention (NEPSY Auditory Attention (AA) and Response Set (RS) and a talker discrimination task (TD)) and short-term memory (visual digit and symbol spans). Results Consistent with the findings reported in the original Eisenberg et al. (2002) study, we found that children perceived noise-vocoded lexically easy words better than lexically hard words. Words in sentences were also recognized better than the same words presented in isolation. No significant correlations were observed between noise-vocoded speech recognition scores and the PPVT-4 using language quotients to control for age effects. However, children who scored higher on the EVT-2 recognized lexically easy words better than lexically hard words in sentences. Older children perceived noise-vocoded speech better than younger children. Finally, we found that measures of auditory attention and short-term memory capacity were significantly correlated with a child’s ability to perceive noise-vocoded isolated words and sentences. Conclusions First, we successfully replicated the major findings from the Eisenberg et al. (2002) study. Because familiarity, phonological distinctiveness and lexical competition affect word recognition, these findings provide additional support for the proposal that several foundational elementary neurocognitive processes underlie the perception of spectrally-degraded speech. Second, we found strong and significant correlations between performance on neurocognitive measures and children’s ability to recognize words and sentences noise-vocoded to four spectral channels. These findings extend earlier research suggesting that perception of spectrally-degraded speech reflects early peripheral auditory processes as well as additional contributions of executive function, specifically, selective attention and short-term memory processes in spoken word recognition. The present findings suggest that auditory attention and short-term memory support robust spoken word recognition in children with NH even under compromised and challenging listening conditions. These results are relevant to research carried out with listeners who have hearing loss, since they are routinely required to encode, process and understand spectrally-degraded acoustic signals. PMID:28045787

Perception of Sung Speech in Bimodal Cochlear Implant Users.

PubMed

Crew, Joseph D; Galvin, John J; Fu, Qian-Jie

2016-11-11

Combined use of a hearing aid (HA) and cochlear implant (CI) has been shown to improve CI users' speech and music performance. However, different hearing devices, test stimuli, and listening tasks may interact and obscure bimodal benefits. In this study, speech and music perception were measured in bimodal listeners for CI-only, HA-only, and CI + HA conditions, using the Sung Speech Corpus, a database of monosyllabic words produced at different fundamental frequencies. Sentence recognition was measured using sung speech in which pitch was held constant or varied across words, as well as for spoken speech. Melodic contour identification (MCI) was measured using sung speech in which the words were held constant or varied across notes. Results showed that sentence recognition was poorer with sung speech relative to spoken, with little difference between sung speech with a constant or variable pitch; mean performance was better with CI-only relative to HA-only, and best with CI + HA. MCI performance was better with constant words versus variable words; mean performance was better with HA-only than with CI-only and was best with CI + HA. Relative to CI-only, a strong bimodal benefit was observed for speech and music perception. Relative to the better ear, bimodal benefits remained strong for sentence recognition but were marginal for MCI. While variations in pitch and timbre may negatively affect CI users' speech and music perception, bimodal listening may partially compensate for these deficits. © The Author(s) 2016.

Selected Topics from LVCSR Research for Asian Languages at Tokyo Tech

NASA Astrophysics Data System (ADS)

Furui, Sadaoki

This paper presents our recent work in regard to building Large Vocabulary Continuous Speech Recognition (LVCSR) systems for the Thai, Indonesian, and Chinese languages. For Thai, since there is no word boundary in the written form, we have proposed a new method for automatically creating word-like units from a text corpus, and applied topic and speaking style adaptation to the language model to recognize spoken-style utterances. For Indonesian, we have applied proper noun-specific adaptation to acoustic modeling, and rule-based English-to-Indonesian phoneme mapping to solve the problem of large variation in proper noun and English word pronunciation in a spoken-query information retrieval system. In spoken Chinese, long organization names are frequently abbreviated, and abbreviated utterances cannot be recognized if the abbreviations are not included in the dictionary. We have proposed a new method for automatically generating Chinese abbreviations, and by expanding the vocabulary using the generated abbreviations, we have significantly improved the performance of spoken query-based search.

Sperry Univac speech communications technology

NASA Technical Reports Server (NTRS)

Medress, Mark F.

1977-01-01

Technology and systems for effective verbal communication with computers were developed. A continuous speech recognition system for verbal input, a word spotting system to locate key words in conversational speech, prosodic tools to aid speech analysis, and a prerecorded voice response system for speech output are described.

Assistive Technology and Adults with Learning Disabilities: A Blueprint for Exploration and Advancement.

ERIC Educational Resources Information Center

Raskind, Marshall

1993-01-01

This article describes assistive technologies for persons with learning disabilities, including word processing, spell checking, proofreading programs, outlining/"brainstorming" programs, abbreviation expanders, speech recognition, speech synthesis/screen review, optical character recognition systems, personal data managers, free-form databases,…

Speech Recognition for A Digital Video Library.

ERIC Educational Resources Information Center

Witbrock, Michael J.; Hauptmann, Alexander G.

1998-01-01

Production of the meta-data supporting the Informedia Digital Video Library interface is automated using techniques derived from artificial intelligence research. Speech recognition and natural-language processing, information retrieval, and image analysis are applied to produce an interface that helps users locate information and navigate more…

Subband-Based Group Delay Segmentation of Spontaneous Speech into Syllable-Like Units

NASA Astrophysics Data System (ADS)

Nagarajan, T.; Murthy, H. A.

2004-12-01

In the development of a syllable-centric automatic speech recognition (ASR) system, segmentation of the acoustic signal into syllabic units is an important stage. Although the short-term energy (STE) function contains useful information about syllable segment boundaries, it has to be processed before segment boundaries can be extracted. This paper presents a subband-based group delay approach to segment spontaneous speech into syllable-like units. This technique exploits the additive property of the Fourier transform phase and the deconvolution property of the cepstrum to smooth the STE function of the speech signal and make it suitable for syllable boundary detection. By treating the STE function as a magnitude spectrum of an arbitrary signal, a minimum-phase group delay function is derived. This group delay function is found to be a better representative of the STE function for syllable boundary detection. Although the group delay function derived from the STE function of the speech signal contains segment boundaries, the boundaries are difficult to determine in the context of long silences, semivowels, and fricatives. In this paper, these issues are specifically addressed and algorithms are developed to improve the segmentation performance. The speech signal is first passed through a bank of three filters, corresponding to three different spectral bands. The STE functions of these signals are computed. Using these three STE functions, three minimum-phase group delay functions are derived. By combining the evidence derived from these group delay functions, the syllable boundaries are detected. Further, a multiresolution-based technique is presented to overcome the problem of shift in segment boundaries during smoothing. Experiments carried out on the Switchboard and OGI-MLTS corpora show that the error in segmentation is at most 25 milliseconds for 67% and 76.6% of the syllable segments, respectively.

Automatic evaluation of hypernasality based on a cleft palate speech database.

PubMed

He, Ling; Zhang, Jing; Liu, Qi; Yin, Heng; Lech, Margaret; Huang, Yunzhi

2015-05-01

The hypernasality is one of the most typical characteristics of cleft palate (CP) speech. The evaluation outcome of hypernasality grading decides the necessity of follow-up surgery. Currently, the evaluation of CP speech is carried out by experienced speech therapists. However, the result strongly depends on their clinical experience and subjective judgment. This work aims to propose an automatic evaluation system for hypernasality grading in CP speech. The database tested in this work is collected by the Hospital of Stomatology, Sichuan University, which has the largest number of CP patients in China. Based on the production process of hypernasality, source sound pulse and vocal tract filter features are presented. These features include pitch, the first and second energy amplified frequency bands, cepstrum based features, MFCC, short-time energy in the sub-bands features. These features combined with KNN classier are applied to automatically classify four grades of hypernasality: normal, mild, moderate and severe. The experiment results show that the proposed system achieves a good performance. The classification rates for four hypernasality grades reach up to 80.4%. The sensitivity of proposed features to the gender is also discussed.

Speech as a pilot input medium

NASA Technical Reports Server (NTRS)

Plummer, R. P.; Coler, C. R.

1977-01-01

The speech recognition system under development is a trainable pattern classifier based on a maximum-likelihood technique. An adjustable uncertainty threshold allows the rejection of borderline cases for which the probability of misclassification is high. The syntax of the command language spoken may be used as an aid to recognition, and the system adapts to changes in pronunciation if feedback from the user is available. Words must be separated by .25 second gaps. The system runs in real time on a mini-computer (PDP 11/10) and was tested on 120,000 speech samples from 10- and 100-word vocabularies. The results of these tests were 99.9% correct recognition for a vocabulary consisting of the ten digits, and 99.6% recognition for a 100-word vocabulary of flight commands, with a 5% rejection rate in each case. With no rejection, the recognition accuracies for the same vocabularies were 99.5% and 98.6% respectively.

Listeners Experience Linguistic Masking Release in Noise-Vocoded Speech-in-Speech Recognition

ERIC Educational Resources Information Center

Viswanathan, Navin; Kokkinakis, Kostas; Williams, Brittany T.

2018-01-01

Purpose: The purpose of this study was to evaluate whether listeners with normal hearing perceiving noise-vocoded speech-in-speech demonstrate better intelligibility of target speech when the background speech was mismatched in language (linguistic release from masking [LRM]) and/or location (spatial release from masking [SRM]) relative to the…

Detection of target phonemes in spontaneous and read speech.

PubMed

Mehta, G; Cutler, A

1988-01-01

Although spontaneous speech occurs more frequently in most listeners' experience than read speech, laboratory studies of human speech recognition typically use carefully controlled materials read from a script. The phonological and prosodic characteristics of spontaneous and read speech differ considerably, however, which suggests that laboratory results may not generalise to the recognition of spontaneous speech. In the present study listeners were presented with both spontaneous and read speech materials, and their response time to detect word-initial target phonemes was measured. Responses were, overall, equally fast in each speech mode. However, analysis of effects previously reported in phoneme detection studies revealed significant differences between speech modes. In read speech but not in spontaneous speech, later targets were detected more rapidly than targets preceded by short words. In contrast, in spontaneous speech but not in read speech, targets were detected more rapidly in accented than in unaccented words and in strong than in weak syllables. An explanation for this pattern is offered in terms of characteristic prosodic differences between spontaneous and read speech. The results support claims from previous work that listeners pay great attention to prosodic information in the process of recognising speech.

Primary Progressive Speech Abulia.

PubMed

Milano, Nicholas J; Heilman, Kenneth M

2015-01-01

Primary progressive aphasia (PPA) is a neurodegenerative disorder characterized by progressive language impairment. The three variants of PPA include the nonfluent/agrammatic, semantic, and logopenic types. The goal of this report is to describe two patients with a loss of speech initiation that was associated with bilateral medial frontal atrophy. Two patients with progressive speech deficits were evaluated and their examinations revealed a paucity of spontaneous speech; however their naming, repetition, reading, and writing were all normal. The patients had no evidence of agrammatism or apraxia of speech but did have impaired speech fluency. In addition to impaired production of propositional spontaneous speech, these patients had impaired production of automatic speech (e.g., reciting the Lord's Prayer) and singing. Structural brain imaging revealed bilateral medial frontal atrophy in both patients. These patients' language deficits are consistent with a PPA, but they are in the pattern of a dynamic aphasia. Whereas the signs-symptoms of dynamic aphasia have been previously described, to our knowledge these are the first cases associated with predominantly bilateral medial frontal atrophy that impaired both propositional and automatic speech. Thus, this profile may represent a new variant of PPA.

An Analysis of Individual Differences in Recognizing Monosyllabic Words Under the Speech Intelligibility Index Framework

PubMed Central

Shen, Yi; Kern, Allison B.

2018-01-01

Individual differences in the recognition of monosyllabic words, either in isolation (NU6 test) or in sentence context (SPIN test), were investigated under the theoretical framework of the speech intelligibility index (SII). An adaptive psychophysical procedure, namely the quick-band-importance-function procedure, was developed to enable the fitting of the SII model to individual listeners. Using this procedure, the band importance function (i.e., the relative weights of speech information across the spectrum) and the link function relating the SII to recognition scores can be simultaneously estimated while requiring only 200 to 300 trials of testing. Octave-frequency band importance functions and link functions were estimated separately for NU6 and SPIN materials from 30 normal-hearing listeners who were naïve to speech recognition experiments. For each type of speech material, considerable individual differences in the spectral weights were observed in some but not all frequency regions. At frequencies where the greatest intersubject variability was found, the spectral weights were correlated between the two speech materials, suggesting that the variability in spectral weights reflected listener-originated factors. PMID:29532711

Particle Swarm Optimization Based Feature Enhancement and Feature Selection for Improved Emotion Recognition in Speech and Glottal Signals

PubMed Central

Muthusamy, Hariharan; Polat, Kemal; Yaacob, Sazali

2015-01-01

In the recent years, many research works have been published using speech related features for speech emotion recognition, however, recent studies show that there is a strong correlation between emotional states and glottal features. In this work, Mel-frequency cepstralcoefficients (MFCCs), linear predictive cepstral coefficients (LPCCs), perceptual linear predictive (PLP) features, gammatone filter outputs, timbral texture features, stationary wavelet transform based timbral texture features and relative wavelet packet energy and entropy features were extracted from the emotional speech (ES) signals and its glottal waveforms(GW). Particle swarm optimization based clustering (PSOC) and wrapper based particle swarm optimization (WPSO) were proposed to enhance the discerning ability of the features and to select the discriminating features respectively. Three different emotional speech databases were utilized to gauge the proposed method. Extreme learning machine (ELM) was employed to classify the different types of emotions. Different experiments were conducted and the results show that the proposed method significantly improves the speech emotion recognition performance compared to previous works published in the literature. PMID:25799141

Effect of high-frequency spectral components in computer recognition of dysarthric speech based on a Mel-cepstral stochastic model.

PubMed

Polur, Prasad D; Miller, Gerald E

2005-01-01

Computer speech recognition of individuals with dysarthria, such as cerebral palsy patients, requires a robust technique that can handle conditions of very high variability and limited training data. In this study, a hidden Markov model (HMM) was constructed and conditions investigated that would provide improved performance for a dysarthric speech (isolated word) recognition system intended to act as an assistive/control tool. In particular, we investigated the effect of high-frequency spectral components on the recognition rate of the system to determine if they contributed useful additional information to the system. A small-size vocabulary spoken by three cerebral palsy subjects was chosen. Mel-frequency cepstral coefficients extracted with the use of 15 ms frames served as training input to an ergodic HMM setup. Subsequent results demonstrated that no significant useful information was available to the system for enhancing its ability to discriminate dysarthric speech above 5.5 kHz in the current set of dysarthric data. The level of variability in input dysarthric speech patterns limits the reliability of the system. However, its application as a rehabilitation/control tool to assist dysarthric motor-impaired individuals such as cerebral palsy subjects holds sufficient promise.

Application of Business Process Management to drive the deployment of a speech recognition system in a healthcare organization.

PubMed

González Sánchez, María José; Framiñán Torres, José Manuel; Parra Calderón, Carlos Luis; Del Río Ortega, Juan Antonio; Vigil Martín, Eduardo; Nieto Cervera, Jaime

2008-01-01

We present a methodology based on Business Process Management to guide the development of a speech recognition system in a hospital in Spain. The methodology eases the deployment of the system by 1) involving the clinical staff in the process, 2) providing the IT professionals with a description of the process and its requirements, 3) assessing advantages and disadvantages of the speech recognition system, as well as its impact in the organisation, and 4) help reorganising the healthcare process before implementing the new technology in order to identify how it can better contribute to the overall objective of the organisation.

Psychometric Functions for Shortened Administrations of a Speech Recognition Approach Using Tri-Word Presentations and Phonemic Scoring

ERIC Educational Resources Information Center

Gelfand, Stanley A.; Gelfand, Jessica T.

2012-01-01

Method: Complete psychometric functions for phoneme and word recognition scores at 8 signal-to-noise ratios from -15 dB to 20 dB were generated for the first 10, 20, and 25, as well as all 50, three-word presentations of the Tri-Word or Computer Assisted Speech Recognition Assessment (CASRA) Test (Gelfand, 1998) based on the results of 12…

Age-related Effects on Word Recognition: Reliance on Cognitive Control Systems with Structural Declines in Speech-responsive Cortex

PubMed Central

Walczak, Adam; Ahlstrom, Jayne; Denslow, Stewart; Horwitz, Amy; Dubno, Judy R.

2008-01-01

Speech recognition can be difficult and effortful for older adults, even for those with normal hearing. Declining frontal lobe cognitive control has been hypothesized to cause age-related speech recognition problems. This study examined age-related changes in frontal lobe function for 15 clinically normal hearing adults (21–75 years) when they performed a word recognition task that was made challenging by decreasing word intelligibility. Although there were no age-related changes in word recognition, there were age-related changes in the degree of activity within left middle frontal gyrus (MFG) and anterior cingulate (ACC) regions during word recognition. Older adults engaged left MFG and ACC regions when words were most intelligible compared to younger adults who engaged these regions when words were least intelligible. Declining gray matter volume within temporal lobe regions responsive to word intelligibility significantly predicted left MFG activity, even after controlling for total gray matter volume, suggesting that declining structural integrity of brain regions responsive to speech leads to the recruitment of frontal regions when words are easily understood. Electronic supplementary material The online version of this article (doi:10.1007/s10162-008-0113-3) contains supplementary material, which is available to authorized users. PMID:18274825

An audiovisual emotion recognition system

NASA Astrophysics Data System (ADS)

Han, Yi; Wang, Guoyin; Yang, Yong; He, Kun

2007-12-01

Human emotions could be expressed by many bio-symbols. Speech and facial expression are two of them. They are both regarded as emotional information which is playing an important role in human-computer interaction. Based on our previous studies on emotion recognition, an audiovisual emotion recognition system is developed and represented in this paper. The system is designed for real-time practice, and is guaranteed by some integrated modules. These modules include speech enhancement for eliminating noises, rapid face detection for locating face from background image, example based shape learning for facial feature alignment, and optical flow based tracking algorithm for facial feature tracking. It is known that irrelevant features and high dimensionality of the data can hurt the performance of classifier. Rough set-based feature selection is a good method for dimension reduction. So 13 speech features out of 37 ones and 10 facial features out of 33 ones are selected to represent emotional information, and 52 audiovisual features are selected due to the synchronization when speech and video fused together. The experiment results have demonstrated that this system performs well in real-time practice and has high recognition rate. Our results also show that the work in multimodules fused recognition will become the trend of emotion recognition in the future.

The Relationship Between Spectral Modulation Detection and Speech Recognition: Adult Versus Pediatric Cochlear Implant Recipients

PubMed Central

Noble, Jack H.; Camarata, Stephen M.; Sunderhaus, Linsey W.; Dwyer, Robert T.; Dawant, Benoit M.; Dietrich, Mary S.; Labadie, Robert F.

2018-01-01

Adult cochlear implant (CI) recipients demonstrate a reliable relationship between spectral modulation detection and speech understanding. Prior studies documenting this relationship have focused on postlingually deafened adult CI recipients—leaving an open question regarding the relationship between spectral resolution and speech understanding for adults and children with prelingual onset of deafness. Here, we report CI performance on the measures of speech recognition and spectral modulation detection for 578 CI recipients including 477 postlingual adults, 65 prelingual adults, and 36 prelingual pediatric CI users. The results demonstrated a significant correlation between spectral modulation detection and various measures of speech understanding for 542 adult CI recipients. For 36 pediatric CI recipients, however, there was no significant correlation between spectral modulation detection and speech understanding in quiet or in noise nor was spectral modulation detection significantly correlated with listener age or age at implantation. These findings suggest that pediatric CI recipients might not depend upon spectral resolution for speech understanding in the same manner as adult CI recipients. It is possible that pediatric CI users are making use of different cues, such as those contained within the temporal envelope, to achieve high levels of speech understanding. Further investigation is warranted to investigate the relationship between spectral and temporal resolution and speech recognition to describe the underlying mechanisms driving peripheral auditory processing in pediatric CI users. PMID:29716437

Speech Recognition Using Multiple Features and Multiple Recognizers

DTIC Science & Technology

1991-12-03

6 2.1 Introduction ............................................... 6 2.2 Human Speech Communication Process...119 How to Setup ASRT.......................................... 119 How to Use Interactive Menus .................................. 120...recognize a word from an acoustic signal. The human ear and brain perform this type of recognition with incredible speed and precision. Even though

End-to-End Multimodal Emotion Recognition Using Deep Neural Networks

NASA Astrophysics Data System (ADS)

Tzirakis, Panagiotis; Trigeorgis, George; Nicolaou, Mihalis A.; Schuller, Bjorn W.; Zafeiriou, Stefanos

2017-12-01

Automatic affect recognition is a challenging task due to the various modalities emotions can be expressed with. Applications can be found in many domains including multimedia retrieval and human computer interaction. In recent years, deep neural networks have been used with great success in determining emotional states. Inspired by this success, we propose an emotion recognition system using auditory and visual modalities. To capture the emotional content for various styles of speaking, robust features need to be extracted. To this purpose, we utilize a Convolutional Neural Network (CNN) to extract features from the speech, while for the visual modality a deep residual network (ResNet) of 50 layers. In addition to the importance of feature extraction, a machine learning algorithm needs also to be insensitive to outliers while being able to model the context. To tackle this problem, Long Short-Term Memory (LSTM) networks are utilized. The system is then trained in an end-to-end fashion where - by also taking advantage of the correlations of the each of the streams - we manage to significantly outperform the traditional approaches based on auditory and visual handcrafted features for the prediction of spontaneous and natural emotions on the RECOLA database of the AVEC 2016 research challenge on emotion recognition.

Feature Selection for Speech Emotion Recognition in Spanish and Basque: On the Use of Machine Learning to Improve Human-Computer Interaction

PubMed Central

Arruti, Andoni; Cearreta, Idoia; Álvarez, Aitor; Lazkano, Elena; Sierra, Basilio

2014-01-01

Study of emotions in human–computer interaction is a growing research area. This paper shows an attempt to select the most significant features for emotion recognition in spoken Basque and Spanish Languages using different methods for feature selection. RekEmozio database was used as the experimental data set. Several Machine Learning paradigms were used for the emotion classification task. Experiments were executed in three phases, using different sets of features as classification variables in each phase. Moreover, feature subset selection was applied at each phase in order to seek for the most relevant feature subset. The three phases approach was selected to check the validity of the proposed approach. Achieved results show that an instance-based learning algorithm using feature subset selection techniques based on evolutionary algorithms is the best Machine Learning paradigm in automatic emotion recognition, with all different feature sets, obtaining a mean of 80,05% emotion recognition rate in Basque and a 74,82% in Spanish. In order to check the goodness of the proposed process, a greedy searching approach (FSS-Forward) has been applied and a comparison between them is provided. Based on achieved results, a set of most relevant non-speaker dependent features is proposed for both languages and new perspectives are suggested. PMID:25279686

[Improvement in Phoneme Discrimination in Noise in Normal Hearing Adults].

PubMed

Schumann, A; Garea Garcia, L; Hoppe, U

2017-02-01

Objective: The study's aim was to examine the possibility to train phoneme-discrimination in noise with normal hearing adults, and its effectivity on speech recognition in noise. A specific computerised training program was used, consisting of special nonsense-syllables with background noise, to train participants' discrimination ability. Material and Methods: 46 normal hearing subjects took part in this study, 28 as training group participants, 18 as control group participants. Only the training group subjects were asked to train over a period of 3 weeks, twice a week for an hour with a computer-based training program. Speech recognition in noise were measured pre- to posttraining for the training group subjects with the Freiburger Einsilber Test. The control group subjects obtained test and restest measures within a 2-3 week break. For the training group follow-up speech recognition was measured 2-3 months after the end of the training. Results: The majority of training group subjects improved their phoneme discrimination significantly. Besides, their speech recognition in noise improved significantly during the training compared to the control group, and remained stable for a period of time. Conclusions: Phonem-Discrimination in noise can be trained by normal hearing adults. The improvements have got a positiv effect on speech recognition in noise, also for a longer period of time. © Georg Thieme Verlag KG Stuttgart · New York.

Recognition and localization of speech by adult cochlear implant recipients wearing a digital hearing aid in the nonimplanted ear (bimodal hearing).

PubMed

Potts, Lisa G; Skinner, Margaret W; Litovsky, Ruth A; Strube, Michael J; Kuk, Francis

2009-06-01

The use of bilateral amplification is now common clinical practice for hearing aid users but not for cochlear implant recipients. In the past, most cochlear implant recipients were implanted in one ear and wore only a monaural cochlear implant processor. There has been recent interest in benefits arising from bilateral stimulation that may be present for cochlear implant recipients. One option for bilateral stimulation is the use of a cochlear implant in one ear and a hearing aid in the opposite nonimplanted ear (bimodal hearing). This study evaluated the effect of wearing a cochlear implant in one ear and a digital hearing aid in the opposite ear on speech recognition and localization. A repeated-measures correlational study was completed. Nineteen adult Cochlear Nucleus 24 implant recipients participated in the study. The participants were fit with a Widex Senso Vita 38 hearing aid to achieve maximum audibility and comfort within their dynamic range. Soundfield thresholds, loudness growth, speech recognition, localization, and subjective questionnaires were obtained six-eight weeks after the hearing aid fitting. Testing was completed in three conditions: hearing aid only, cochlear implant only, and cochlear implant and hearing aid (bimodal). All tests were repeated four weeks after the first test session. Repeated-measures analysis of variance was used to analyze the data. Significant effects were further examined using pairwise comparison of means or in the case of continuous moderators, regression analyses. The speech-recognition and localization tasks were unique, in that a speech stimulus presented from a variety of roaming azimuths (140 degree loudspeaker array) was used. Performance in the bimodal condition was significantly better for speech recognition and localization compared to the cochlear implant-only and hearing aid-only conditions. Performance was also different between these conditions when the location (i.e., side of the loudspeaker array that presented the word) was analyzed. In the bimodal condition, the speech-recognition and localization tasks were equal regardless of which side of the loudspeaker array presented the word, while performance was significantly poorer for the monaural conditions (hearing aid only and cochlear implant only) when the words were presented on the side with no stimulation. Binaural loudness summation of 1-3 dB was seen in soundfield thresholds and loudness growth in the bimodal condition. Measures of the audibility of sound with the hearing aid, including unaided thresholds, soundfield thresholds, and the Speech Intelligibility Index, were significant moderators of speech recognition and localization. Based on the questionnaire responses, participants showed a strong preference for bimodal stimulation. These findings suggest that a well-fit digital hearing aid worn in conjunction with a cochlear implant is beneficial to speech recognition and localization. The dynamic test procedures used in this study illustrate the importance of bilateral hearing for locating, identifying, and switching attention between multiple speakers. It is recommended that unilateral cochlear implant recipients, with measurable unaided hearing thresholds, be fit with a hearing aid.

The Effectiveness of Clear Speech as a Masker

ERIC Educational Resources Information Center

Calandruccio, Lauren; Van Engen, Kristin; Dhar, Sumitrajit; Bradlow, Ann R.

2010-01-01

Purpose: It is established that speaking clearly is an effective means of enhancing intelligibility. Because any signal-processing scheme modeled after known acoustic-phonetic features of clear speech will likely affect both target and competing speech, it is important to understand how speech recognition is affected when a competing speech signal…

Visual speech information: a help or hindrance in perceptual processing of dysarthric speech.

PubMed

Borrie, Stephanie A

2015-03-01

This study investigated the influence of visual speech information on perceptual processing of neurologically degraded speech. Fifty listeners identified spastic dysarthric speech under both audio (A) and audiovisual (AV) conditions. Condition comparisons revealed that the addition of visual speech information enhanced processing of the neurologically degraded input in terms of (a) acuity (percent phonemes correct) of vowels and consonants and (b) recognition (percent words correct) of predictive and nonpredictive phrases. Listeners exploited stress-based segmentation strategies more readily in AV conditions, suggesting that the perceptual benefit associated with adding visual speech information to the auditory signal-the AV advantage-has both segmental and suprasegmental origins. Results also revealed that the magnitude of the AV advantage can be predicted, to some degree, by the extent to which an individual utilizes syllabic stress cues to inform word recognition in AV conditions. Findings inform the development of a listener-specific model of speech perception that applies to processing of dysarthric speech in everyday communication contexts.

Processing F0 with cochlear implants: Modulation frequency discrimination and speech intonation recognition.

PubMed

Chatterjee, Monita; Peng, Shu-Chen

2008-01-01

Fundamental frequency (F0) processing by cochlear implant (CI) listeners was measured using a psychophysical task and a speech intonation recognition task. Listeners' Weber fractions for modulation frequency discrimination were measured using an adaptive, 3-interval, forced-choice paradigm: stimuli were presented through a custom research interface. In the speech intonation recognition task, listeners were asked to indicate whether resynthesized bisyllabic words, when presented in the free field through the listeners' everyday speech processor, were question-like or statement-like. The resynthesized tokens were systematically manipulated to have different initial-F0s to represent male vs. female voices, and different F0 contours (i.e. falling, flat, and rising) Although the CI listeners showed considerable variation in performance on both tasks, significant correlations were observed between the CI listeners' sensitivity to modulation frequency in the psychophysical task and their performance in intonation recognition. Consistent with their greater reliance on temporal cues, the CI listeners' performance in the intonation recognition task was significantly poorer with the higher initial-F0 stimuli than with the lower initial-F0 stimuli. Similar results were obtained with normal hearing listeners attending to noiseband-vocoded CI simulations with reduced spectral resolution.

Processing F0 with Cochlear Implants: Modulation Frequency Discrimination and Speech Intonation Recognition

PubMed Central

Chatterjee, Monita; Peng, Shu-Chen

2008-01-01

Fundamental frequency (F0) processing by cochlear implant (CI) listeners was measured using a psychophysical task and a speech intonation recognition task. Listeners’ Weber fractions for modulation frequency discrimination were measured using an adaptive, 3-interval, forced-choice paradigm: stimuli were presented through a custom research interface. In the speech intonation recognition task, listeners were asked to indicate whether resynthesized bisyllabic words, when presented in the free field through the listeners’ everyday speech processor, were question-like or statement-like. The resynthesized tokens were systematically manipulated to have different initial F0s to represent male vs. female voices, and different F0 contours (i.e., falling, flat, and rising) Although the CI listeners showed considerable variation in performance on both tasks, significant correlations were observed between the CI listeners’ sensitivity to modulation frequency in the psychophysical task and their performance in intonation recognition. Consistent with their greater reliance on temporal cues, the CI listeners’ performance in the intonation recognition task was significantly poorer with the higher initial-F0 stimuli than with the lower initial-F0 stimuli. Similar results were obtained with normal hearing listeners attending to noiseband-vocoded CI simulations with reduced spectral resolution. PMID:18093766

Benefits of adaptive FM systems on speech recognition in noise for listeners who use hearing aids.

PubMed

Thibodeau, Linda

2010-06-01

To compare the benefits of adaptive FM and fixed FM systems through measurement of speech recognition in noise with adults and students in clinical and real-world settings. Five adults and 5 students with moderate-to-severe hearing loss completed objective and subjective speech recognition in noise measures with the 2 types of FM processing. Sentence recognition was evaluated in a classroom for 5 competing noise levels ranging from 54 to 80 dBA while the FM microphone was positioned 6 in. from the signal loudspeaker to receive input at 84 dB SPL. The subjective measures included 2 classroom activities and 6 auditory lessons in a noisy, public aquarium. On the objective measures, adaptive FM processing resulted in significantly better speech recognition in noise than fixed FM processing for 68- and 73-dBA noise levels. On the subjective measures, all individuals preferred adaptive over fixed processing for half of the activities. Adaptive processing was also preferred by most (8-9) individuals for the remaining 4 activities. The adaptive FM processing resulted in significant improvements at the higher noise levels and was preferred by the majority of participants in most of the conditions.

Working Memory and Speech Recognition in Noise Under Ecologically Relevant Listening Conditions: Effects of Visual Cues and Noise Type Among Adults With Hearing Loss.

PubMed

Miller, Christi W; Stewart, Erin K; Wu, Yu-Hsiang; Bishop, Christopher; Bentler, Ruth A; Tremblay, Kelly

2017-08-16

This study evaluated the relationship between working memory (WM) and speech recognition in noise with different noise types as well as in the presence of visual cues. Seventy-six adults with bilateral, mild to moderately severe sensorineural hearing loss (mean age: 69 years) participated. Using a cross-sectional design, 2 measures of WM were taken: a reading span measure, and Word Auditory Recognition and Recall Measure (Smith, Pichora-Fuller, & Alexander, 2016). Speech recognition was measured with the Multi-Modal Lexical Sentence Test for Adults (Kirk et al., 2012) in steady-state noise and 4-talker babble, with and without visual cues. Testing was under unaided conditions. A linear mixed model revealed visual cues and pure-tone average as the only significant predictors of Multi-Modal Lexical Sentence Test outcomes. Neither WM measure nor noise type showed a significant effect. The contribution of WM in explaining unaided speech recognition in noise was negligible and not influenced by noise type or visual cues. We anticipate that with audibility partially restored by hearing aids, the effects of WM will increase. For clinical practice to be affected, more significant effect sizes are needed.

Neuronal Spoken Word Recognition: The Time Course of Processing Variation in the Speech Signal

ERIC Educational Resources Information Center

Schild, Ulrike; Roder, Brigitte; Friedrich, Claudia K.

2012-01-01

Recent neurobiological studies revealed evidence for lexical representations that are not specified for the coronal place of articulation (PLACE; Friedrich, Eulitz, & Lahiri, 2006; Friedrich, Lahiri, & Eulitz, 2008). Here we tested when these types of underspecified representations influence neuronal speech recognition. In a unimodal…

Recognizing Speech under a Processing Load: Dissociating Energetic from Informational Factors

ERIC Educational Resources Information Center

Mattys, Sven L.; Brooks, Joanna; Cooke, Martin

2009-01-01

Effects of perceptual and cognitive loads on spoken-word recognition have so far largely escaped investigation. This study lays the foundations of a psycholinguistic approach to speech recognition in adverse conditions that draws upon the distinction between energetic masking, i.e., listening environments leading to signal degradation, and…

Bilingual Computerized Speech Recognition Screening for Depression Symptoms

ERIC Educational Resources Information Center

Gonzalez, Gerardo; Carter, Colby; Blanes, Erika

2007-01-01

The Voice-Interactive Depression Assessment System (VIDAS) is a computerized speech recognition application for screening depression based on the Center for Epidemiological Studies--Depression scale in English and Spanish. Study 1 included 50 English and 47 Spanish speakers. Study 2 involved 108 English and 109 Spanish speakers. Participants…

Multichannel Compression, Temporal Cues, and Audibility.

ERIC Educational Resources Information Center

Souza, Pamela E.; Turner, Christopher W.

1998-01-01

The effect of the reduction of the temporal envelope produced by multichannel compression on recognition was examined in 16 listeners with hearing loss, with particular focus on audibility of the speech signal. Multichannel compression improved speech recognition when superior audibility was provided by a two-channel compression system over linear…

The effect of hearing aid technologies on listening in an automobile.

PubMed

Wu, Yu-Hsiang; Stangl, Elizabeth; Bentler, Ruth A; Stanziola, Rachel W

2013-06-01

Communication while traveling in an automobile often is very difficult for hearing aid users. This is because the automobile/road noise level is usually high, and listeners/drivers often do not have access to visual cues. Since the talker of interest usually is not located in front of the listener/driver, conventional directional processing that places the directivity beam toward the listener's front may not be helpful and, in fact, could have a negative impact on speech recognition (when compared to omnidirectional processing). Recently, technologies have become available in commercial hearing aids that are designed to improve speech recognition and/or listening effort in noisy conditions where talkers are located behind or beside the listener. These technologies include (1) a directional microphone system that uses a backward-facing directivity pattern (Back-DIR processing), (2) a technology that transmits audio signals from the ear with the better signal-to-noise ratio (SNR) to the ear with the poorer SNR (Side-Transmission processing), and (3) a signal processing scheme that suppresses the noise at the ear with the poorer SNR (Side-Suppression processing). The purpose of the current study was to determine the effect of (1) conventional directional microphones and (2) newer signal processing schemes (Back-DIR, Side-Transmission, and Side-Suppression) on listener's speech recognition performance and preference for communication in a traveling automobile. A single-blinded, repeated-measures design was used. Twenty-five adults with bilateral symmetrical sensorineural hearing loss aged 44 through 84 yr participated in the study. The automobile/road noise and sentences of the Connected Speech Test (CST) were recorded through hearing aids in a standard van moving at a speed of 70 mph on a paved highway. The hearing aids were programmed to omnidirectional microphone, conventional adaptive directional microphone, and the three newer schemes. CST sentences were presented from the side and back of the hearing aids, which were placed on the ears of a manikin. The recorded stimuli were presented to listeners via earphones in a sound-treated booth to assess speech recognition performance and preference with each programmed condition. Compared to omnidirectional microphones, conventional adaptive directional processing had a detrimental effect on speech recognition when speech was presented from the back or side of the listener. Back-DIR and Side-Transmission processing improved speech recognition performance (relative to both omnidirectional and adaptive directional processing) when speech was from the back and side, respectively. The performance with Side-Suppression processing was better than with adaptive directional processing when speech was from the side. The participants' preferences for a given processing scheme were generally consistent with speech recognition results. The finding that performance with adaptive directional processing was poorer than with omnidirectional microphones demonstrates the importance of selecting the correct microphone technology for different listening situations. The results also suggest the feasibility of using hearing aid technologies to provide a better listening experience for hearing aid users in automobiles. American Academy of Audiology.

Not all sounds sound the same: Parkinson's disease affects differently emotion processing in music and in speech prosody.

PubMed

Lima, César F; Garrett, Carolina; Castro, São Luís

2013-01-01

Does emotion processing in music and speech prosody recruit common neurocognitive mechanisms? To examine this question, we implemented a cross-domain comparative design in Parkinson's disease (PD). Twenty-four patients and 25 controls performed emotion recognition tasks for music and spoken sentences. In music, patients had impaired recognition of happiness and peacefulness, and intact recognition of sadness and fear; this pattern was independent of general cognitive and perceptual abilities. In speech, patients had a small global impairment, which was significantly mediated by executive dysfunction. Hence, PD affected differently musical and prosodic emotions. This dissociation indicates that the mechanisms underlying the two domains are partly independent.

Tell it like it is.

PubMed

Lee, S L

2000-05-01

Nurses, therapists and case managers were spending too much time each week on the phone waiting to read patient reports to live transcriptionists who would then type the reports for storage in VNSNY's clinical management mainframe database. A speech recognition system helped solve the problem by providing the staff 24-hour access to an automated transcription service any day of the week. Nurses and case managers no longer wait in long queues to transmit patient reports or to retrieve information from the database. Everything is done automatically within minutes. VNSNY saved both time and money by updating its transcription strategy. Now nurses can spend more time with patients and less time on the phone transcribing notes. It also means fewer staff members are needed on weekends to do manual transcribing.

Speech-on-speech masking with variable access to the linguistic content of the masker speech for native and nonnative english speakers.

PubMed

Calandruccio, Lauren; Bradlow, Ann R; Dhar, Sumitrajit

2014-04-01

Masking release for an English sentence-recognition task in the presence of foreign-accented English speech compared with native-accented English speech was reported in Calandruccio et al (2010a). The masking release appeared to increase as the masker intelligibility decreased. However, it could not be ruled out that spectral differences between the speech maskers were influencing the significant differences observed. The purpose of the current experiment was to minimize spectral differences between speech maskers to determine how various amounts of linguistic information within competing speech Affiliationect masking release. A mixed-model design with within-subject (four two-talker speech maskers) and between-subject (listener group) factors was conducted. Speech maskers included native-accented English speech and high-intelligibility, moderate-intelligibility, and low-intelligibility Mandarin-accented English. Normalizing the long-term average speech spectra of the maskers to each other minimized spectral differences between the masker conditions. Three listener groups were tested, including monolingual English speakers with normal hearing, nonnative English speakers with normal hearing, and monolingual English speakers with hearing loss. The nonnative English speakers were from various native language backgrounds, not including Mandarin (or any other Chinese dialect). Listeners with hearing loss had symmetric mild sloping to moderate sensorineural hearing loss. Listeners were asked to repeat back sentences that were presented in the presence of four different two-talker speech maskers. Responses were scored based on the key words within the sentences (100 key words per masker condition). A mixed-model regression analysis was used to analyze the difference in performance scores between the masker conditions and listener groups. Monolingual English speakers with normal hearing benefited when the competing speech signal was foreign accented compared with native accented, allowing for improved speech recognition. Various levels of intelligibility across the foreign-accented speech maskers did not influence results. Neither the nonnative English-speaking listeners with normal hearing nor the monolingual English speakers with hearing loss benefited from masking release when the masker was changed from native-accented to foreign-accented English. Slight modifications between the target and the masker speech allowed monolingual English speakers with normal hearing to improve their recognition of native-accented English, even when the competing speech was highly intelligible. Further research is needed to determine which modifications within the competing speech signal caused the Mandarin-accented English to be less effective with respect to masking. Determining the influences within the competing speech that make it less effective as a masker or determining why monolingual normal-hearing listeners can take advantage of these differences could help improve speech recognition for those with hearing loss in the future. American Academy of Audiology.

Application of speech recognition and synthesis in the general aviation cockpit

NASA Technical Reports Server (NTRS)

North, R. A.; Mountford, S. J.; Bergeron, H.

1984-01-01

Interactive speech recognition/synthesis technology is assessed as a method for the aleviation of single-pilot IFR flight workloads. Attention was given during this series of evaluations to the conditions typical of general aviation twin-engine aircrft cockpits, covering several commonly encountered IFR flight condition scenarios. The most beneficial speech command tasks are noted to be in the data retrieval domain, which would allow the pilot access to uplinked data, checklists, and performance charts. Data entry tasks also appear to benefit from this technology.

Noise-immune multisensor transduction of speech

NASA Astrophysics Data System (ADS)

Viswanathan, Vishu R.; Henry, Claudia M.; Derr, Alan G.; Roucos, Salim; Schwartz, Richard M.

1986-08-01

Two types of configurations of multiple sensors were developed, tested and evaluated in speech recognition application for robust performance in high levels of acoustic background noise: One type combines the individual sensor signals to provide a single speech signal input, and the other provides several parallel inputs. For single-input systems, several configurations of multiple sensors were developed and tested. Results from formal speech intelligibility and quality tests in simulated fighter aircraft cockpit noise show that each of the two-sensor configurations tested outperforms the constituent individual sensors in high noise. Also presented are results comparing the performance of two-sensor configurations and individual sensors in speaker-dependent, isolated-word speech recognition tests performed using a commercial recognizer (Verbex 4000) in simulated fighter aircraft cockpit noise.

Evaluation of speech recognizers for use in advanced combat helicopter crew station research and development

NASA Technical Reports Server (NTRS)

Simpson, Carol A.

1990-01-01

The U.S. Army Crew Station Research and Development Facility uses vintage 1984 speech recognizers. An evaluation was performed of newer off-the-shelf speech recognition devices to determine whether newer technology performance and capabilities are substantially better than that of the Army's current speech recognizers. The Phonetic Discrimination (PD-100) Test was used to compare recognizer performance in two ambient noise conditions: quiet office and helicopter noise. Test tokens were spoken by males and females and in isolated-word and connected-work mode. Better overall recognition accuracy was obtained from the newer recognizers. Recognizer capabilities needed to support the development of human factors design requirements for speech command systems in advanced combat helicopters are listed.

"Who" is saying "what"? Brain-based decoding of human voice and speech.

PubMed

Formisano, Elia; De Martino, Federico; Bonte, Milene; Goebel, Rainer

2008-11-07

Can we decipher speech content ("what" is being said) and speaker identity ("who" is saying it) from observations of brain activity of a listener? Here, we combine functional magnetic resonance imaging with a data-mining algorithm and retrieve what and whom a person is listening to from the neural fingerprints that speech and voice signals elicit in the listener's auditory cortex. These cortical fingerprints are spatially distributed and insensitive to acoustic variations of the input so as to permit the brain-based recognition of learned speech from unknown speakers and of learned voices from previously unheard utterances. Our findings unravel the detailed cortical layout and computational properties of the neural populations at the basis of human speech recognition and speaker identification.

Effects of noise on speech recognition: Challenges for communication by service members.

PubMed

Le Prell, Colleen G; Clavier, Odile H

2017-06-01

Speech communication often takes place in noisy environments; this is an urgent issue for military personnel who must communicate in high-noise environments. The effects of noise on speech recognition vary significantly according to the sources of noise, the number and types of talkers, and the listener's hearing ability. In this review, speech communication is first described as it relates to current standards of hearing assessment for military and civilian populations. The next section categorizes types of noise (also called maskers) according to their temporal characteristics (steady or fluctuating) and perceptive effects (energetic or informational masking). Next, speech recognition difficulties experienced by listeners with hearing loss and by older listeners are summarized, and questions on the possible causes of speech-in-noise difficulty are discussed, including recent suggestions of "hidden hearing loss". The final section describes tests used by military and civilian researchers, audiologists, and hearing technicians to assess performance of an individual in recognizing speech in background noise, as well as metrics that predict performance based on a listener and background noise profile. This article provides readers with an overview of the challenges associated with speech communication in noisy backgrounds, as well as its assessment and potential impact on functional performance, and provides guidance for important new research directions relevant not only to military personnel, but also to employees who work in high noise environments. Copyright © 2016 Elsevier B.V. All rights reserved.